diff --git a/data/xml/2021.acl.xml b/data/xml/2021.acl.xml
index 6fc5cf57b9..cbf1f5df9e 100644
--- a/data/xml/2021.acl.xml
+++ b/data/xml/2021.acl.xml
@@ -12689,6 +12689,15 @@
       <url hash="8e86a5da">2021.acl-tutorials.1</url>
       <doi>10.18653/v1/2021.acl-tutorials.1</doi>
       <bibkey>bar-haim-etal-2021-advances</bibkey>
+      <video href="2021.acl-tutorials.1.1.mp4"/>
+      <video href="2021.acl-tutorials.1.2.mp4"/>
+      <video href="2021.acl-tutorials.1.3.mp4"/>
+      <video href="2021.acl-tutorials.1.4.mp4"/>
+      <video href="2021.acl-tutorials.1.5.mp4"/>
+      <video href="2021.acl-tutorials.1.6.mp4"/>
+      <video href="2021.acl-tutorials.1.7.mp4"/>
+      <video href="2021.acl-tutorials.1.8.mp4"/>
+      <video href="2021.acl-tutorials.1.9.mp4"/>
     </paper>
     <paper id="2">
       <title>Event-Centric Natural Language Processing</title>
@@ -12704,6 +12713,7 @@
       <url hash="d82826b3">2021.acl-tutorials.2</url>
       <doi>10.18653/v1/2021.acl-tutorials.2</doi>
       <bibkey>chen-etal-2021-event</bibkey>
+      <video href="2021.acl-tutorials.2.mp4"/>
     </paper>
     <paper id="3">
       <title>Meta Learning and Its Applications to Natural Language Processing</title>
@@ -12725,6 +12735,9 @@
       <url hash="bae9900f">2021.acl-tutorials.4</url>
       <doi>10.18653/v1/2021.acl-tutorials.4</doi>
       <bibkey>wang-li-2021-pre</bibkey>
+      <video href="2021.acl-tutorials.4.1.mp4"/>
+      <video href="2021.acl-tutorials.4.2.mp4"/>
+      <video href="2021.acl-tutorials.4.3.mp4"/>
     </paper>
     <paper id="5">
       <title>Prosody: Models, Methods, and Applications</title>
@@ -12765,6 +12778,166 @@
     </paper>
   </volume>
   <event id="acl-2021">
+    <meta>
+      <title>59th Annual Meeting of the Association for Computational Linguistics</title>
+      <location>Online</location>
+      <dates>August 1–6, 2021</dates>
+    </meta>
+    <links>
+      <url type="website">https://2021.aclweb.org</url>
+    </links>
+    <talk>
+      <title>Keynote 1: Advancing Technological Equity in Speech and Language Processing</title>
+      <speaker><first>Helen</first><last>Meng</last></speaker>
+      <url type="video">2021.acl.keynote1.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 2: Learning and Processing Language from Wearables: Opportunities and Challenges</title>
+      <speaker><first>Alejandrina</first><last>Cristia</last></speaker>
+      <url type="video">2021.acl.keynote2.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 3: Reliable Characterizations of <fixed-case>NLP</fixed-case> Systems as a Social Responsibility</title>
+      <speaker><first>Christopher</first><last>Potts</last></speaker>
+      <url type="video">2021.acl.keynote3.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session</title>
+      <speaker><first>Chengqing</first><last>Zong</last></speaker>
+      <speaker><first>Roberto</first><last>Navigli</last></speaker>
+      <speaker><first>Fei</first><last>Xia</last></speaker>
+      <speaker><first>Wenjie</first><last>Li</last></speaker>
+      <url type="video">2021.acl.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Presidential Address</title>
+      <speaker><first>Rada</first><last>Mihalcea</last></speaker>
+      <url type="video">2021.acl.presidential-address.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Business Manager Report</title>
+      <speaker><first>Priscilla</first><last>Rasmussen</last></speaker>
+      <url type="video">2021.acl.business-meeting1.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Conference Officer Report</title>
+      <speaker><first>Yusuke</first><last>Miyao</last></speaker>
+      <url type="video">2021.acl.business-meeting2.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>EACL</fixed-case> Report</title>
+      <speaker><first>Shuly</first><last>Wintner</last></speaker>
+      <url type="video">2021.acl.business-meeting3.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>NAACL</fixed-case> Report</title>
+      <speaker><first>Colin</first><last>Cherry</last></speaker>
+      <url type="video">2021.acl.business-meeting4.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>CL</fixed-case> Report</title>
+      <speaker><first>Hwee Tou</first><last>Ng</last></speaker>
+      <url type="video">2021.acl.business-meeting5.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>TACL</fixed-case> Report</title>
+      <speaker><first>Brian</first><last>Roark</last></speaker>
+      <url type="video">2021.acl.business-meeting6.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>ACL</fixed-case> <fixed-case>R</fixed-case>olling <fixed-case>R</fixed-case>eview Report</title>
+      <speaker><first>Amanda</first><last>Stent</last></speaker>
+      <url type="video">2021.acl.business-meeting7.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>ACL</fixed-case> <fixed-case>A</fixed-case>nthology Report</title>
+      <speaker><first>Matt</first><last>Post</last></speaker>
+      <url type="video">2021.acl.business-meeting8.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Professional Conduct Committee Report</title>
+      <speaker><first>Graeme</first><last>Hirst</last></speaker>
+      <speaker><first>Emily M.</first><last>Bender</last></speaker>
+      <url type="video">2021.acl.business-meeting9.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Publicity Director Report</title>
+      <speaker><first>Barbara</first><last>Plank</last></speaker>
+      <speaker><first>Sarvnaz</first><last>Karimi</last></speaker>
+      <speaker><first>Caroline</first><last>Lawrence</last></speaker>
+      <url type="video">2021.acl.business-meeting10.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Secretary's Report</title>
+      <speaker><first>Shiqi</first><last>Zhao</last></speaker>
+      <url type="video">2021.acl.business-meeting11.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Treasurer's Report</title>
+      <speaker><first>David</first><last>Yarowsky</last></speaker>
+      <url type="video">2021.acl.business-meeting12.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Sponsorship Director Report</title>
+      <speaker><first>Chris</first><last>Callison-Burch</last></speaker>
+      <url type="video">2021.acl.business-meeting13.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>ACL</fixed-case> 2023 Call for Bids</title>
+      <speaker><first>Timothy</first><last>Baldwin</last></speaker>
+      <url type="video">2021.acl.business-meeting111.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>ACL</fixed-case> 2024 Call for Bids</title>
+      <speaker><first>Iryna</first><last>Gurevych</last></speaker>
+      <url type="video">2021.acl.business-meeting121.mp4</url>
+    </talk>
+    <talk>
+      <title>Panel: Green <fixed-case>NLP</fixed-case></title>
+      <speaker><first>Roy</first><last>Schwartz</last></speaker>
+      <speaker><first>Colin</first><last>Raffel</last></speaker>
+      <speaker><first>Phil</first><last>Blunsom</last></speaker>
+      <speaker><first>Jesse</first><last>Dodge</last></speaker>
+      <speaker><first>Yuki</first><last>Arase</last></speaker>
+      <speaker><first>Noah A.</first><last>Smith</last></speaker>
+      <speaker><first>Emma</first><last>Strubell</last></speaker>
+      <speaker><first>Percy</first><last>Liang</last></speaker>
+      <speaker><first>Mona</first><last>Diab</last></speaker>
+      <speaker><first>Iryna</first><last>Gurevych</last></speaker>
+      <speaker><first>Yue</first><last>Zhang</last></speaker>
+      <url type="video">2021.acl.panel.mp4</url>
+    </talk>
+    <talk>
+      <title>Distinguished Service Awards and Test of Time Awards Session</title>
+      <speaker><first>Rada</first><last>Mihalcea</last></speaker>
+      <url type="video">2021.acl.test-of-time-award.mp4</url>
+    </talk>
+    <talk>
+      <title>Lifetime Achievement Award Session</title>
+      <speaker><first>Rada</first><last>Mihalcea</last></speaker>
+      <speaker><first>Junichi</first><last>Tsujii</last></speaker>
+      <url type="video">2021.acl.lifetime-achievement-award.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session</title>
+      <speaker><first>Timothy</first><last>Baldwin</last></speaker>
+      <url type="video">2021.acl.best-papers.mp4</url>
+    </talk>
+    <talk>
+      <title>Closing Session</title>
+      <speaker><first>Chengqing</first><last>Zong</last></speaker>
+      <speaker><first>Bonnie</first><last>Weber</last></speaker>
+      <speaker><first>Anna</first><last>Korhonen</last></speaker>
+      <speaker><first>Vivek</first><last>Gupta</last></speaker>
+      <speaker><first>David</first><last>Trye</last></speaker>
+      <speaker><first>Marie-Francine</first><last>Moens</last></speaker>
+      <speaker><first>Dan</first><last>Roth</last></speaker>
+      <speaker><first>Chu-Ren</first><last>Huang</last></speaker>
+      <speaker><first>Roberto</first><last>Navigli</last></speaker>
+      <speaker><first>Fei</first><last>Xia</last></speaker>
+      <speaker><first>Maggie</first><last>Li</last></speaker>
+      <url type="video">2021.acl.closing-session.mp4</url>
+    </talk>
     <colocated>
       <volume-id>2021.findings-acl</volume-id>
       <volume-id>2021.bppf-1</volume-id>
diff --git a/data/xml/2021.emnlp.xml b/data/xml/2021.emnlp.xml
index 4600208ef9..227d1d963c 100644
--- a/data/xml/2021.emnlp.xml
+++ b/data/xml/2021.emnlp.xml
@@ -14140,6 +14140,49 @@
     </paper>
   </volume>
   <event id="emnlp-2021">
+    <meta>
+      <title>The 2021 Conference on Empirical Methods in Natural Language Processing</title>
+      <location>Punta Cana, Dominican Republic</location>
+      <dates>November 7-11, 2021</dates>
+    </meta>
+    <links>
+      <url type="website">https://2021.emnlp.org</url>
+      <url type="handbook">2021.emnlp.handbook.pdf</url>
+    </links>
+    <talk>
+      <title>Keynote 1: Where next? Towards multi-text consumption via three inspired research lines</title>
+      <speaker><first>Ido</first><last>Dagan</last></speaker>
+      <url type="video">2021.emnlp.keynote1.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 2: The language system in the human brain</title>
+      <speaker><first>Evelina</first><last>Fedorenko</last></speaker>
+      <url type="video">2021.emnlp.keynote2.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 3: <fixed-case>LT4All</fixed-case>!? Rethinking the Agenda</title>
+      <speaker><first>Steven</first><last>Bird</last></speaker>
+      <url type="video">2021.emnlp.keynote3.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session</title>
+      <speaker><first>Sien</first><last>Moens</last></speaker>
+      <speaker><first>Xuanjing</first><last>Huang</last></speaker>
+      <speaker><first>Lucia</first><last>Specia</last></speaker>
+      <speaker><first>Scott</first><last>Yih</last></speaker>
+      <url type="video">2021.emnlp.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session and Closing Session</title>
+      <speaker><first>Sien</first><last>Moens</last></speaker>
+      <speaker><first>Lucia</first><last>Specia</last></speaker>
+      <speaker><first>Preslav</first><last>Nakov</last></speaker>
+      <speaker><first>Dan</first><last>Roth</last></speaker>
+      <speaker><first>Key-Sun</first><last>Choi</last></speaker>
+      <speaker><first>Noah A.</first><last>Smith</last></speaker>
+      <speaker><first>Chia-Hui</first><last>Chang</last></speaker>
+      <url type="video">2021.emnlp.closing-session.mp4</url>
+    </talk>
     <colocated>
       <volume-id>2021.findings-emnlp</volume-id>
       <volume-id>2021.codi-main</volume-id>
diff --git a/data/xml/2021.naacl.xml b/data/xml/2021.naacl.xml
index b35ac7caab..bcb6a82f88 100644
--- a/data/xml/2021.naacl.xml
+++ b/data/xml/2021.naacl.xml
@@ -8093,6 +8093,11 @@
       <doi>10.18653/v1/2021.naacl-tutorials.5</doi>
       <bibkey>beltagy-etal-2021-beyond</bibkey>
       <pwccode url="https://github.com/allenai/naacl2021-longdoc-tutorial" additional="false">allenai/naacl2021-longdoc-tutorial</pwccode>
+      <video href="2021.naacl-tutorials.5.1.mp4"/>
+      <video href="2021.naacl-tutorials.5.2.mp4"/>
+      <video href="2021.naacl-tutorials.5.3.mp4"/>
+      <video href="2021.naacl-tutorials.5.4.mp4"/>
+      <video href="2021.naacl-tutorials.5.5.mp4"/>
     </paper>
     <paper id="6">
       <title>Crowdsourcing Natural Language Data at Scale: A Hands-On Tutorial</title>
@@ -8718,6 +8723,98 @@
     </paper>
   </volume>
   <event id="naacl-2021">
+    <meta>
+      <title>2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics</title>
+      <location>Online</location>
+      <dates>June 6-11, 2021</dates>
+    </meta>
+    <links>
+      <url type="website">https://2021.naacl.org</url>
+    </links>
+    <talk>
+      <title>Keynote 1: Humans Learn From Task Descriptions and So Should Our Models</title>
+      <speaker><first>Hinrich</first><last>Schütze</last></speaker>
+      <url type="video">2021.naacl.keynote1.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 2: From Disembodied to Embodied Multimodal Learning</title>
+      <speaker><first>Dhruv</first><last>Batra</last></speaker>
+      <url type="video">2021.naacl.keynote2.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 3: Generating Reality: Technical and Social Explorations in Generative Machine Learning Research</title>
+      <speaker><first>Shakir</first><last>Mohamed</last></speaker>
+      <url type="video">2021.naacl.keynote3.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 4: Moving the Needle in <fixed-case>NLP</fixed-case> Technology for the Processing of Code-switched Language</title>
+      <speaker><first>Thamar</first><last>Solorio</last></speaker>
+      <url type="video">2021.naacl.keynote4.mp4</url>
+    </talk>
+    <talk>
+      <title>Industry Track Keynote 1: Project Debater - from grand challenge to business applications, behind the scenes and lessons learned</title>
+      <speaker><first>Aya</first><last>Soffer</last></speaker>
+      <url type="video">2021.naacl.keynote_industry1.mp4</url>
+    </talk>
+    <talk>
+      <title>Industry Track Keynote 2: <fixed-case>S</fixed-case>emantic <fixed-case>S</fixed-case>cholar - Advanced <fixed-case>NLP</fixed-case> to Accelerate Scientific Research</title>
+      <speaker><first>Dan</first><last>Weld</last></speaker>
+      <url type="video">2021.naacl.keynote_industry2.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session</title>
+      <speaker><first>Kristina</first><last>Toutanova</last></speaker>
+      <speaker><first>Anna</first><last>Rumshisky</last></speaker>
+      <speaker><first>Luke</first><last>Zettlemoyer</last></speaker>
+      <speaker><first>Dilek</first><last>Hakkani-Tur</last></speaker>
+      <url type="video">2021.naacl.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting</title>
+      <speaker><first>Colin</first><last>Cherry</last></speaker>
+      <speaker><first>Jon</first><last>May</last></speaker>
+      <speaker><first>Amittai</first><last>Axelrod</last></speaker>
+      <speaker><first>Luciana</first><last>Benotti</last></speaker>
+      <speaker><first>Owen</first><last>Rambow</last></speaker>
+      <speaker><first>Vivek</first><last>Gupta</last></speaker>
+      <speaker><first>Anna</first><last>Rumshisky</last></speaker>
+      <speaker><first>Marie-Francine</first><last>Moens</last></speaker>
+      <speaker><first>Bernardo</first><last>Magnini</last></speaker>
+      <url type="video">2021.naacl.business-meeting.mp4</url>
+    </talk>
+    <talk>
+      <title>Panel: Careers in <fixed-case>NLP</fixed-case></title>
+      <speaker><first>Isabelle</first><last>Augenstein</last></speaker>
+      <speaker><first>Mona</first><last>Diab</last></speaker>
+      <speaker><first>Jimmy</first><last>Lin</last></speaker>
+      <speaker><first>Sebastian</first><last>Ruder</last></speaker>
+      <speaker><first>Philip</first><last>Resnik</last></speaker>
+      <url type="video">2021.naacl.panel1.mp4</url>
+    </talk>
+    <talk>
+      <title>Panel: Startups in <fixed-case>NLP</fixed-case></title>
+      <speaker><first>Apoorv</first><last>Agarwal</last></speaker>
+      <speaker><first>Spence</first><last>Green</last></speaker>
+      <speaker><first>Nasrin</first><last>Mostafazadeh</last></speaker>
+      <speaker><first>Kieran</first><last>Snyder</last></speaker>
+      <speaker><first>Alon</first><last>Lavie</last></speaker>
+      <url type="video">2021.naacl.panel2.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session</title>
+      <speaker><first>Anna</first><last>Rumshisky</last></speaker>
+      <url type="video">2021.naacl.best-papers.mp4</url>
+    </talk>
+    <talk>
+      <title>Closing Session</title>
+      <speaker><first>Kristina</first><last>Toutanova</last></speaker>
+      <speaker><first>Avi</first><last>Sil</last></speaker>
+      <speaker><first>Victoria</first><last>Lin</last></speaker>
+      <speaker><first>Marie-Francine</first><last>Moens</last></speaker>
+      <speaker><first>Dan</first><last>Roth</last></speaker>
+      <speaker><first>Bernardo</first><last>Magnini</last></speaker>
+      <url type="video">2021.naacl.closing-session.mp4</url>
+    </talk>
     <colocated>
       <volume-id>2021.alvr-1</volume-id>
       <volume-id>2021.americasnlp-1</volume-id>
diff --git a/data/xml/2022.acl.xml b/data/xml/2022.acl.xml
index 16b60c47b5..4272f3e549 100644
--- a/data/xml/2022.acl.xml
+++ b/data/xml/2022.acl.xml
@@ -3537,6 +3537,7 @@
       <doi>10.18653/v1/2022.acl-long.220</doi>
       <pwccode url="https://github.com/thomaslu2000/incremental-parsing-representations" additional="false">thomaslu2000/incremental-parsing-representations</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/penn-treebank">Penn Treebank</pwcdataset>
+      <video href="2022.acl-long.220.mp4"/>
     </paper>
     <paper id="221">
       <title>Knowledge Enhanced Reflection Generation for Counseling Dialogues</title>
@@ -4797,6 +4798,7 @@ in the Case of Unambiguous Gender</title>
       <revision id="1" href="2022.acl-long.298v1" hash="3dd88706"/>
       <revision id="2" href="2022.acl-long.298v2" hash="39fb17fa" date="2022-05-21">Various fixes throughout the paper.</revision>
       <doi>10.18653/v1/2022.acl-long.298</doi>
+      <video href="2022.acl-long.298.mp4"/>
     </paper>
     <paper id="299">
       <title>Improving Word Translation via Two-Stage Contrastive Learning</title>
@@ -8223,6 +8225,7 @@ in the Case of Unambiguous Gender</title>
       <bibkey>pine-etal-2022-requirements</bibkey>
       <doi>10.18653/v1/2022.acl-long.507</doi>
       <pwccode url="https://github.com/roedoejet/fastspeech2" additional="false">roedoejet/fastspeech2</pwccode>
+      <video href="2022.acl-long.507.mp4"/>
     </paper>
     <paper id="508">
       <title>Sharpness-Aware Minimization Improves Language Model Generalization</title>
@@ -12269,6 +12272,8 @@ in the Case of Unambiguous Gender</title>
       <bibkey>church-etal-2022-gentle</bibkey>
       <doi>10.18653/v1/2022.acl-tutorials.1</doi>
       <pwcdataset url="https://paperswithcode.com/dataset/glue">GLUE</pwcdataset>
+      <video href="2022.acl-tutorials.1.1.mp4"/>
+      <video href="2022.acl-tutorials.1.2.mp4"/>
     </paper>
     <paper id="2">
       <title>Towards Reproducible Machine Learning Research in Natural Language Processing</title>
@@ -12285,6 +12290,8 @@ in the Case of Unambiguous Gender</title>
       <url hash="06b2f824">2022.acl-tutorials.2</url>
       <bibkey>lucic-etal-2022-towards</bibkey>
       <doi>10.18653/v1/2022.acl-tutorials.2</doi>
+      <video href="2022.acl-tutorials.2.1.mp4"/>
+      <video href="2022.acl-tutorials.2.2.mp4"/>
     </paper>
     <paper id="3">
       <title>Knowledge-Augmented Methods for Natural Language Processing</title>
@@ -12303,6 +12310,10 @@ in the Case of Unambiguous Gender</title>
       <pwcdataset url="https://paperswithcode.com/dataset/commonsenseqa">CommonsenseQA</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/conceptnet">ConceptNet</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/riddle-sense">RiddleSense</pwcdataset>
+      <video href="2022.acl-tutorials.3.1.mp4"/>
+      <video href="2022.acl-tutorials.3.2.mp4"/>
+      <video href="2022.acl-tutorials.3.3.mp4"/>
+      <video href="2022.acl-tutorials.3.4.mp4"/>
     </paper>
     <paper id="4">
       <title>Non-Autoregressive Sequence Generation</title>
@@ -12313,6 +12324,8 @@ in the Case of Unambiguous Gender</title>
       <url hash="a91a6086">2022.acl-tutorials.4</url>
       <bibkey>gu-tan-2022-non</bibkey>
       <doi>10.18653/v1/2022.acl-tutorials.4</doi>
+      <video href="2022.acl-tutorials.4.1.mp4"/>
+      <video href="2022.acl-tutorials.4.2.mp4"/>
     </paper>
     <paper id="5">
       <title>Learning with Limited Text Data</title>
@@ -12324,6 +12337,7 @@ in the Case of Unambiguous Gender</title>
       <url hash="fe4ec2d3">2022.acl-tutorials.5</url>
       <bibkey>yang-etal-2022-learning</bibkey>
       <doi>10.18653/v1/2022.acl-tutorials.5</doi>
+      <video href="2022.acl-tutorials.5.mp4"/>
     </paper>
     <paper id="6">
       <title>Zero- and Few-Shot <fixed-case>NLP</fixed-case> with Pretrained Language Models</title>
@@ -12337,6 +12351,8 @@ in the Case of Unambiguous Gender</title>
       <url hash="2e1a3511">2022.acl-tutorials.6</url>
       <bibkey>beltagy-etal-2022-zero</bibkey>
       <doi>10.18653/v1/2022.acl-tutorials.6</doi>
+      <video href="2022.acl-tutorials.6.1.mp4"/>
+      <video href="2022.acl-tutorials.6.2.mp4"/>
     </paper>
     <paper id="7">
       <title>Vision-Language Pretraining: Current Trends and the Future</title>
@@ -12349,6 +12365,9 @@ in the Case of Unambiguous Gender</title>
       <bibkey>agrawal-etal-2022-vision</bibkey>
       <doi>10.18653/v1/2022.acl-tutorials.7</doi>
       <pwcdataset url="https://paperswithcode.com/dataset/visual-question-answering">Visual Question Answering</pwcdataset>
+      <video href="2022.acl-tutorials.7.1.mp4"/>
+      <video href="2022.acl-tutorials.7.2.mp4"/>
+      <video href="2022.acl-tutorials.7.3.mp4"/>
     </paper>
     <paper id="8">
       <title>Natural Language Processing for Multilingual Task-Oriented Dialogue</title>
@@ -12362,6 +12381,8 @@ in the Case of Unambiguous Gender</title>
       <url hash="c8809ed6">2022.acl-tutorials.8</url>
       <bibkey>razumovskaia-etal-2022-natural</bibkey>
       <doi>10.18653/v1/2022.acl-tutorials.8</doi>
+      <video href="2022.acl-tutorials.8.1.mp4"/>
+      <video href="2022.acl-tutorials.8.2.mp4"/>
     </paper>
   </volume>
   <event id="acl-2022">
@@ -12386,13 +12407,119 @@ in the Case of Unambiguous Gender</title>
       <url type="video">2022.acl.keynote2.mp4</url>
     </talk>
     <talk>
-      <title>ACL business meeting</title>
+      <title>The Next Big Ideas Talks</title>
+      <speaker><first>Marco</first><last>Baroni</last></speaker>
+      <speaker><first>Eduard</first><last>Hovy</last></speaker>
+      <speaker><first>Heng</first><last>Ji</last></speaker>
+      <speaker><first>Mirella</first><last>Lapata</last></speaker>
+      <speaker><first>Hang</first><last>Li</last></speaker>
+      <speaker><first>Dan</first><last>Roth</last></speaker>
+      <speaker><first>Thamar</first><last>Solorio</last></speaker>
+      <url type="video">2022.acl.next-big-ideas.mp4</url>
+    </talk>
+    <talk>
+      <title>Spotlight Talks for Young Rising Stars</title>
+      <speaker><first>Eunsol</first><last>Choi</last></speaker>
+      <speaker><first>Ryan</first><last>Cotterell</last></speaker>
+      <speaker><first>Sebastian</first><last>Ruder</last></speaker>
+      <speaker><first>Swabha</first><last>Swayamdipta</last></speaker>
+      <speaker><first>Diyi</first><last>Yang</last></speaker>
+      <url type="video">2022.acl.spotlight-talks.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session and Presidential Address</title>
+      <speaker><first>Bernardo</first><last>Magnini</last></speaker>
+      <speaker><first>Andy</first><last>Way</last></speaker>
+      <speaker><first>John</first><last>Kelleher</last></speaker>
+      <speaker><first>Preslav</first><last>Nakov</last></speaker>
+      <speaker><first>Aline</first><last>Villavicencio</last></speaker>
+      <speaker><first>Smaranda</first><last>Muresan</last></speaker>
+      <speaker><first>Mona</first><last>Diab</last></speaker>
       <speaker><first>Timothy</first><last>Baldwin</last></speaker>
-      <speaker><first>David</first><last>Yarowsky</last></speaker>
-      <speaker><first>Rada</first><last>Mihalcea</last></speaker>
-      <speaker><first>Emily M.</first><last>Bender</last></speaker>
+      <url type="video">2022.acl.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>TACL</fixed-case> Report</title>
+      <speaker><first>Brian</first><last>Roark</last></speaker>
+      <url type="video">2022.acl.business-meeting1.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Secretary's Report</title>
+      <speaker><first>Shiqi</first><last>Zhao</last></speaker>
+      <url type="video">2022.acl.business-meeting2.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>EACL</fixed-case> Report</title>
+      <speaker><first>Shuly</first><last>Wintner</last></speaker>
+      <url type="video">2022.acl.business-meeting3.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>ACL</fixed-case> 2024 Coordinating Committee Report</title>
       <speaker><first>Iryna</first><last>Gurevych</last></speaker>
-      <url type="video">2022.acl.business-meeting.mp4</url>
+      <url type="video">2022.acl.business-meeting4.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>NAACL</fixed-case> Chair Report</title>
+      <speaker><first>Luciana</first><last>Benotti</last></speaker>
+      <url type="video">2022.acl.business-meeting5.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Sponsorship Director Report</title>
+      <speaker><first>Chris</first><last>Callison-Burch</last></speaker>
+      <url type="video">2022.acl.business-meeting6.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Professional Conduct Committee Report</title>
+      <speaker><first>Graeme</first><last>Hirst</last></speaker>
+      <speaker><first>Emily M.</first><last>Bender</last></speaker>
+      <url type="video">2022.acl.business-meeting7.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Ethics Committee Report</title>
+      <speaker><first>Min-Yen</first><last>Kan</last></speaker>
+      <url type="video">2022.acl.business-meeting8.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Conference Officer Report</title>
+      <speaker><first>Yusuke</first><last>Miyao</last></speaker>
+      <url type="video">2022.acl.business-meeting9.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Publicity Director Report</title>
+      <speaker><first>Barbara</first><last>Plank</last></speaker>
+      <url type="video">2022.acl.business-meeting10.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: <fixed-case>ACL</fixed-case> 2025 Call for Bids</title>
+      <speaker><first>Emily M.</first><last>Bender</last></speaker>
+      <url type="video">2022.acl.business-meeting11.mp4</url>
+    </talk>
+    <talk>
+      <title>Awards Ceremony</title>
+      <speaker><first>Timothy</first><last>Baldwin</last></speaker>
+      <speaker><first>Yusuke</first><last>Miyao</last></speaker>
+      <url type="video">2022.acl.awards-ceremony.mp4</url>
+    </talk>
+    <talk>
+      <title>EMNLP 2022 Information Session</title>
+      <speaker><first>Nizar</first><last>Habash</last></speaker>
+      <url type="video">2022.acl.emnlp-2022.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session</title>
+      <speaker><first>Bernardo</first><last>Magnini</last></speaker>
+      <url type="video">2022.acl.best-papers.mp4</url>
+    </talk>
+    <talk>
+      <title>Closing Session</title>
+      <speaker><first>Bernardo</first><last>Magnini</last></speaker>
+      <speaker><first>Dan</first><last>Roth</last></speaker>
+      <speaker><first>Key-Sun</first><last>Choi</last></speaker>
+      <speaker><first>Nizar</first><last>Habash</last></speaker>
+      <speaker><first>Alessandro</first><last>Moschitti</last></speaker>
+      <speaker><first>Yulan</first><last>He</last></speaker>
+      <speaker><first>Mona</first><last>Diab</last></speaker>
+      <url type="video">2022.acl.closing-session.mp4</url>
     </talk>
     <colocated>
       <volume-id>2022.findings-acl</volume-id>
diff --git a/data/xml/2022.bea.xml b/data/xml/2022.bea.xml
index cd7e534504..d2e01871e8 100644
--- a/data/xml/2022.bea.xml
+++ b/data/xml/2022.bea.xml
@@ -74,6 +74,7 @@
       <url hash="c462e340">2022.bea-1.4</url>
       <bibkey>chen-etal-2022-automatically</bibkey>
       <doi>10.18653/v1/2022.bea-1.4</doi>
+      <video href="2022.bea-1.4.mp4"/>
     </paper>
     <paper id="5">
       <title>A Baseline Readability Model for <fixed-case>C</fixed-case>ebuano</title>
diff --git a/data/xml/2022.bigscience.xml b/data/xml/2022.bigscience.xml
index 903aae6694..54462c559e 100644
--- a/data/xml/2022.bigscience.xml
+++ b/data/xml/2022.bigscience.xml
@@ -33,6 +33,7 @@
       <url hash="b618bf84">2022.bigscience-1.1</url>
       <bibkey>jin-etal-2022-lifelong</bibkey>
       <doi>10.18653/v1/2022.bigscience-1.1</doi>
+      <video href="2022.bigscience-1.1.mp4"/>
     </paper>
     <paper id="2">
       <title>Using <fixed-case>ASR</fixed-case>-Generated Text for Spoken Language Modeling</title>
diff --git a/data/xml/2022.cl.xml b/data/xml/2022.cl.xml
index 7f96c1b19f..adfb853ca7 100644
--- a/data/xml/2022.cl.xml
+++ b/data/xml/2022.cl.xml
@@ -397,6 +397,7 @@
       <pages>849–886</pages>
       <url hash="6a8d22fb">2022.cl-4.13</url>
       <bibkey>nivre-etal-2022-nucleus</bibkey>
+      <video href="2022.cl-4.13.mp4"/>
     </paper>
     <paper id="14">
       <title>Effective Approaches to Neural Query Language Identification</title>
@@ -412,6 +413,7 @@
       <pages>887–906</pages>
       <url hash="ea9d6792">2022.cl-4.14</url>
       <bibkey>ren-etal-2022-effective</bibkey>
+      <video href="2022.cl-4.14.mp4"/>
     </paper>
     <paper id="15">
       <title>Information Theory–based Compositional Distributional Semantics</title>
@@ -424,6 +426,7 @@
       <pages>907–948</pages>
       <url hash="e6d93f6e">2022.cl-4.15</url>
       <bibkey>amigo-etal-2022-information</bibkey>
+      <video href="2022.cl-4.15.mp4"/>
     </paper>
     <paper id="16">
       <title>Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Review</title>
@@ -458,6 +461,7 @@
       <pages>1021–1052</pages>
       <url hash="b2d8ead8">2022.cl-4.18</url>
       <bibkey>keya-etal-2022-neural</bibkey>
+      <video href="2022.cl-4.18.mp4"/>
     </paper>
     <paper id="19">
       <title>The Text Anonymization Benchmark (<fixed-case>TAB</fixed-case>): A Dedicated Corpus and Evaluation Framework for Text Anonymization</title>
@@ -472,6 +476,7 @@
       <pages>1053–1101</pages>
       <url hash="e97fa2c7">2022.cl-4.19</url>
       <bibkey>pilan-etal-2022-text</bibkey>
+      <video href="2022.cl-4.19.mp4"/>
     </paper>
     <paper id="20">
       <title>How Much Does Lookahead Matter for Disambiguation? Partial <fixed-case>A</fixed-case>rabic Diacritization Case Study</title>
@@ -483,6 +488,7 @@
       <pages>1103–1123</pages>
       <url hash="7ca73aa5">2022.cl-4.20</url>
       <bibkey>esmail-etal-2022-much</bibkey>
+      <video href="2022.cl-4.20.mp4"/>
     </paper>
     <paper id="21">
       <title>A Metrological Perspective on Reproducibility in <fixed-case>NLP</fixed-case>*</title>
diff --git a/data/xml/2022.emnlp.xml b/data/xml/2022.emnlp.xml
index 7cbc1045ed..b0381e0022 100644
--- a/data/xml/2022.emnlp.xml
+++ b/data/xml/2022.emnlp.xml
@@ -28,6 +28,7 @@
       <url hash="b4d5a267">2022.emnlp-main.1</url>
       <bibkey>ye-etal-2022-generative</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.1</doi>
+      <video href="2022.emnlp-main.1.mp4"/>
     </paper>
     <paper id="2">
       <title><fixed-case>CDC</fixed-case>onv: A Benchmark for Contradiction Detection in <fixed-case>C</fixed-case>hinese Conversations</title>
@@ -45,6 +46,7 @@
       <url hash="e41b50ef">2022.emnlp-main.2</url>
       <bibkey>zheng-etal-2022-cdconv</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.2</doi>
+      <video href="2022.emnlp-main.2.mp4"/>
     </paper>
     <paper id="3">
       <title>Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space</title>
@@ -57,6 +59,7 @@
       <url hash="3799d2bc">2022.emnlp-main.3</url>
       <bibkey>geva-etal-2022-transformer</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.3</doi>
+      <video href="2022.emnlp-main.3.mp4"/>
     </paper>
     <paper id="4">
       <title>Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation</title>
@@ -73,6 +76,7 @@
       <url hash="e74accab">2022.emnlp-main.4</url>
       <bibkey>wang-etal-2022-learning-generate</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.4</doi>
+      <video href="2022.emnlp-main.4.mp4"/>
     </paper>
     <paper id="5">
       <title>Graph-based Model Generation for Few-Shot Relation Extraction</title>
@@ -83,6 +87,7 @@
       <url hash="e850b39c">2022.emnlp-main.5</url>
       <bibkey>li-qian-2022-graph</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.5</doi>
+      <video href="2022.emnlp-main.5.mp4"/>
     </paper>
     <paper id="6">
       <title>Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling</title>
@@ -93,6 +98,7 @@
       <url hash="8e9f5576">2022.emnlp-main.6</url>
       <bibkey>yoo-kwak-2022-backdoor</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.6</doi>
+      <video href="2022.emnlp-main.6.mp4"/>
     </paper>
     <paper id="7">
       <title>Generating Natural Language Proofs with Verifier-Guided Search</title>
@@ -104,6 +110,7 @@
       <url hash="d22b28e1">2022.emnlp-main.7</url>
       <bibkey>yang-etal-2022-generating</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.7</doi>
+      <video href="2022.emnlp-main.7.mp4"/>
     </paper>
     <paper id="8">
       <title>Toward Unifying Text Segmentation and Long Document Summarization</title>
@@ -117,6 +124,7 @@
       <url hash="a94331cb">2022.emnlp-main.8</url>
       <bibkey>cho-etal-2022-toward</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.8</doi>
+      <video href="2022.emnlp-main.8.mp4"/>
     </paper>
     <paper id="9">
       <title>The Geometry of Multilingual Language Model Representations</title>
@@ -128,6 +136,7 @@
       <url hash="982a4a79">2022.emnlp-main.9</url>
       <bibkey>chang-etal-2022-geometry</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.9</doi>
+      <video href="2022.emnlp-main.9.mp4"/>
     </paper>
     <paper id="10">
       <title>Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment</title>
@@ -140,6 +149,7 @@
       <attachment type="software" hash="d5f0189d">2022.emnlp-main.10.software.zip</attachment>
       <bibkey>tang-etal-2022-improving</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.10</doi>
+      <video href="2022.emnlp-main.10.mp4"/>
     </paper>
     <paper id="11">
       <title><fixed-case>PAIR</fixed-case>: Prompt-Aware marg<fixed-case>I</fixed-case>n Ranking for Counselor Reflection Scoring in Motivational Interviewing</title>
@@ -152,6 +162,7 @@
       <url hash="897ccce5">2022.emnlp-main.11</url>
       <bibkey>min-etal-2022-pair</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.11</doi>
+      <video href="2022.emnlp-main.11.mp4"/>
     </paper>
     <paper id="12">
       <title>Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs</title>
@@ -162,6 +173,7 @@
       <url hash="c4610436">2022.emnlp-main.12</url>
       <bibkey>xing-tsang-2022-co</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.12</doi>
+      <video href="2022.emnlp-main.12.mp4"/>
     </paper>
     <paper id="13">
       <title>The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains</title>
@@ -173,6 +185,7 @@
       <url hash="d8b737f7">2022.emnlp-main.13</url>
       <bibkey>xu-etal-2022-importance</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.13</doi>
+      <video href="2022.emnlp-main.13.mp4"/>
     </paper>
     <paper id="14">
       <title>Interpreting Language Models with Contrastive Explanations</title>
@@ -183,6 +196,7 @@
       <url hash="424f4266">2022.emnlp-main.14</url>
       <bibkey>yin-neubig-2022-interpreting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.14</doi>
+      <video href="2022.emnlp-main.14.mp4"/>
     </paper>
     <paper id="15">
       <title><fixed-case>R</fixed-case>ank<fixed-case>G</fixed-case>en: Improving Text Generation with Large Ranking Models</title>
@@ -195,6 +209,7 @@
       <url hash="ed265940">2022.emnlp-main.15</url>
       <bibkey>krishna-etal-2022-rankgen</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.15</doi>
+      <video href="2022.emnlp-main.15.mp4"/>
     </paper>
     <paper id="16">
       <title>Learning a Grammar Inducer from Massive Uncurated Instructional Videos</title>
@@ -210,6 +225,7 @@
       <url hash="29fe9542">2022.emnlp-main.16</url>
       <bibkey>zhang-etal-2022-learning-grammar</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.16</doi>
+      <video href="2022.emnlp-main.16.mp4"/>
     </paper>
     <paper id="17">
       <title>Normalized Contrastive Learning for Text-Video Retrieval</title>
@@ -225,6 +241,7 @@
       <url hash="8aba78d1">2022.emnlp-main.17</url>
       <bibkey>park-etal-2022-normalized</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.17</doi>
+      <video href="2022.emnlp-main.17.mp4"/>
     </paper>
     <paper id="18">
       <title>Estimating Soft Labels for Out-of-Domain Intent Detection</title>
@@ -239,6 +256,7 @@
       <url hash="326e302a">2022.emnlp-main.18</url>
       <bibkey>lang-etal-2022-estimating</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.18</doi>
+      <video href="2022.emnlp-main.18.mp4"/>
     </paper>
     <paper id="19">
       <title>Multi-<fixed-case>VQG</fixed-case>: Generating Engaging Questions for Multiple Images</title>
@@ -251,6 +269,7 @@
       <url hash="95421d25">2022.emnlp-main.19</url>
       <bibkey>yeh-etal-2022-multi</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.19</doi>
+      <video href="2022.emnlp-main.19.mp4"/>
     </paper>
     <paper id="20">
       <title>Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation</title>
@@ -264,6 +283,7 @@
       <url hash="ac04e165">2022.emnlp-main.20</url>
       <bibkey>bulian-etal-2022-tomayto</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.20</doi>
+      <video href="2022.emnlp-main.20.mp4"/>
     </paper>
     <paper id="21">
       <title>Non-Parametric Domain Adaptation for End-to-End Speech Translation</title>
@@ -291,6 +311,7 @@
       <url hash="98f294a0">2022.emnlp-main.22</url>
       <bibkey>cao-etal-2022-prompting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.22</doi>
+      <video href="2022.emnlp-main.22.mp4"/>
     </paper>
     <paper id="23">
       <title>Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking</title>
@@ -304,6 +325,7 @@
       <url hash="8f8a8b23">2022.emnlp-main.23</url>
       <bibkey>li-etal-2022-certified</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.23</doi>
+      <video href="2022.emnlp-main.23.mp4"/>
     </paper>
     <paper id="24">
       <title>Linearizing Transformer with Key-Value Memory</title>
@@ -314,6 +336,7 @@
       <url hash="79a2af54">2022.emnlp-main.24</url>
       <bibkey>zhang-cai-2022-linearizing</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.24</doi>
+      <video href="2022.emnlp-main.24.mp4"/>
     </paper>
     <paper id="25">
       <title>Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions</title>
@@ -326,6 +349,7 @@
       <url hash="03d6a9d0">2022.emnlp-main.25</url>
       <bibkey>verma-etal-2022-robustness</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.25</doi>
+      <video href="2022.emnlp-main.25.mp4"/>
     </paper>
     <paper id="26">
       <title>Translation between Molecules and Natural Language</title>
@@ -340,6 +364,7 @@
       <url hash="42e97673">2022.emnlp-main.26</url>
       <bibkey>edwards-etal-2022-translation</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.26</doi>
+      <video href="2022.emnlp-main.26.mp4"/>
     </paper>
     <paper id="27">
       <title>What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment</title>
@@ -352,6 +377,7 @@
       <url hash="194f4f12">2022.emnlp-main.27</url>
       <bibkey>finlayson-etal-2022-makes</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.27</doi>
+      <video href="2022.emnlp-main.27.mp4"/>
     </paper>
     <paper id="28">
       <title>Sentence-Incremental Neural Coreference Resolution</title>
@@ -364,6 +390,7 @@
       <attachment type="software" hash="69edf3d2">2022.emnlp-main.28.software.zip</attachment>
       <bibkey>grenander-etal-2022-sentence</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.28</doi>
+      <video href="2022.emnlp-main.28.mp4"/>
     </paper>
     <paper id="29">
       <title><fixed-case>SN</fixed-case>a<fixed-case>C</fixed-case>: Coherence Error Detection for Narrative Summarization</title>
@@ -375,6 +402,7 @@
       <url hash="043359c3">2022.emnlp-main.29</url>
       <bibkey>goyal-etal-2022-snac</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.29</doi>
+      <video href="2022.emnlp-main.29.mp4"/>
     </paper>
     <paper id="30">
       <title><fixed-case>H</fixed-case>ydra<fixed-case>S</fixed-case>um: Disentangling Style Features in Text Summarization with Multi-Decoder Models</title>
@@ -387,6 +415,7 @@
       <url hash="c019eef5">2022.emnlp-main.30</url>
       <bibkey>goyal-etal-2022-hydrasum</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.30</doi>
+      <video href="2022.emnlp-main.30.mp4"/>
     </paper>
     <paper id="31">
       <title>A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing</title>
@@ -400,6 +429,7 @@
       <url hash="41f29208">2022.emnlp-main.31</url>
       <bibkey>jin-etal-2022-good-neighbor</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.31</doi>
+      <video href="2022.emnlp-main.31.mp4"/>
     </paper>
     <paper id="32">
       <title>Guiding Neural Entity Alignment with Compatibility</title>
@@ -414,6 +444,7 @@
       <url hash="770825f1">2022.emnlp-main.32</url>
       <bibkey>liu-etal-2022-guiding</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.32</doi>
+      <video href="2022.emnlp-main.32.mp4"/>
     </paper>
     <paper id="33">
       <title><fixed-case>I</fixed-case>nstruct<fixed-case>D</fixed-case>ial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning</title>
@@ -428,6 +459,7 @@
       <url hash="11578ac8">2022.emnlp-main.33</url>
       <bibkey>gupta-etal-2022-instructdial</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.33</doi>
+      <video href="2022.emnlp-main.33.mp4"/>
     </paper>
     <paper id="34">
       <title>Unsupervised Boundary-Aware Language Model Pretraining for <fixed-case>C</fixed-case>hinese Sequence Labeling</title>
@@ -443,6 +475,7 @@
       <attachment type="software" hash="6479e497">2022.emnlp-main.34.software.zip</attachment>
       <bibkey>jiang-etal-2022-unsupervised</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.34</doi>
+      <video href="2022.emnlp-main.34.mp4"/>
     </paper>
     <paper id="35">
       <title><fixed-case>R</fixed-case>etro<fixed-case>MAE</fixed-case>: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder</title>
@@ -455,6 +488,7 @@
       <url hash="84cb8ce1">2022.emnlp-main.35</url>
       <bibkey>xiao-etal-2022-retromae</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.35</doi>
+      <video href="2022.emnlp-main.35.mp4"/>
     </paper>
     <paper id="36">
       <title>Aligning Recommendation and Conversation via Dual Imitation</title>
@@ -470,6 +504,7 @@
       <url hash="f31cea6a">2022.emnlp-main.36</url>
       <bibkey>zhou-etal-2022-aligning</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.36</doi>
+      <video href="2022.emnlp-main.36.mp4"/>
     </paper>
     <paper id="37">
       <title><fixed-case>QR</fixed-case>el<fixed-case>S</fixed-case>core: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance</title>
@@ -483,6 +518,7 @@
       <attachment type="software" hash="e5e411bd">2022.emnlp-main.37.software.zip</attachment>
       <bibkey>wang-etal-2022-qrelscore</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.37</doi>
+      <video href="2022.emnlp-main.37.mp4"/>
     </paper>
     <paper id="38">
       <title>Abstract Visual Reasoning with Tangram Shapes</title>
@@ -498,6 +534,7 @@
       <url hash="6ac23de6">2022.emnlp-main.38</url>
       <bibkey>ji-etal-2022-abstract</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.38</doi>
+      <video href="2022.emnlp-main.38.mp4"/>
     </paper>
     <paper id="39">
       <title><fixed-case>U</fixed-case>nified<fixed-case>SKG</fixed-case>: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models</title>
@@ -529,6 +566,7 @@
       <url hash="e7e0b77f">2022.emnlp-main.39</url>
       <bibkey>xie-etal-2022-unifiedskg</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.39</doi>
+      <video href="2022.emnlp-main.39.mp4"/>
     </paper>
     <paper id="40">
       <title>Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in <fixed-case>NLP</fixed-case> Models</title>
@@ -540,6 +578,7 @@
       <url hash="84d84db6">2022.emnlp-main.40</url>
       <bibkey>chen-etal-2022-balanced</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.40</doi>
+      <video href="2022.emnlp-main.40.mp4"/>
     </paper>
     <paper id="41">
       <title>When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarks</title>
@@ -552,6 +591,7 @@
       <attachment type="software" hash="b0b51ed7">2022.emnlp-main.41.software.zip</attachment>
       <bibkey>sikarwar-etal-2022-transformers</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.41</doi>
+      <video href="2022.emnlp-main.41.mp4"/>
     </paper>
     <paper id="42">
       <title>Generative Language Models for Paragraph-Level Question Generation</title>
@@ -563,6 +603,7 @@
       <url hash="3f32331f">2022.emnlp-main.42</url>
       <bibkey>ushio-etal-2022-generative</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.42</doi>
+      <video href="2022.emnlp-main.42.mp4"/>
     </paper>
     <paper id="43">
       <title>A Unified Encoder-Decoder Framework with Entity Memory</title>
@@ -575,6 +616,7 @@
       <url hash="9d6b838c">2022.emnlp-main.43</url>
       <bibkey>zhang-etal-2022-unified</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.43</doi>
+      <video href="2022.emnlp-main.43.mp4"/>
     </paper>
     <paper id="44">
       <title>Segmenting Numerical Substitution Ciphers</title>
@@ -585,6 +627,7 @@
       <url hash="e4f37b03">2022.emnlp-main.44</url>
       <bibkey>aldarrab-may-2022-segmenting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.44</doi>
+      <video href="2022.emnlp-main.44.mp4"/>
     </paper>
     <paper id="45">
       <title>Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset</title>
@@ -597,6 +640,7 @@
       <url hash="7ac7781c">2022.emnlp-main.45</url>
       <bibkey>thapliyal-etal-2022-crossmodal</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.45</doi>
+      <video href="2022.emnlp-main.45.mp4"/>
     </paper>
     <paper id="46">
       <title><fixed-case>R</fixed-case>e<fixed-case>S</fixed-case>el: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select</title>
@@ -613,6 +657,7 @@
       <url hash="ace5e963">2022.emnlp-main.46</url>
       <bibkey>zhuang-etal-2022-resel</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.46</doi>
+      <video href="2022.emnlp-main.46.mp4"/>
     </paper>
     <paper id="47">
       <title><fixed-case>G</fixed-case>amma<fixed-case>E</fixed-case>: Gamma Embeddings for Logical Queries on Knowledge Graphs</title>
@@ -627,6 +672,7 @@
       <attachment type="software" hash="d779b7d0">2022.emnlp-main.47.software.zip</attachment>
       <bibkey>yang-etal-2022-gammae</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.47</doi>
+      <video href="2022.emnlp-main.47.mp4"/>
     </paper>
     <paper id="48">
       <title>Reasoning Like Program Executors</title>
@@ -644,6 +690,7 @@
       <url hash="5559225b">2022.emnlp-main.48</url>
       <bibkey>pi-etal-2022-reasoning</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.48</doi>
+      <video href="2022.emnlp-main.48.mp4"/>
     </paper>
     <paper id="49">
       <title><fixed-case>SEM</fixed-case>-F1: an Automatic Way for Semantic Evaluation of Multi-Narrative Overlap Summaries at Scale</title>
@@ -655,6 +702,7 @@
       <url hash="efabbc4a">2022.emnlp-main.49</url>
       <bibkey>bansal-etal-2022-sem</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.49</doi>
+      <video href="2022.emnlp-main.49.mp4"/>
     </paper>
     <paper id="50">
       <title>Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning</title>
@@ -669,6 +717,7 @@
       <url hash="3ac7e3a6">2022.emnlp-main.50</url>
       <bibkey>chen-etal-2022-inducer</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.50</doi>
+      <video href="2022.emnlp-main.50.mp4"/>
     </paper>
     <paper id="51">
       <title><fixed-case>D</fixed-case>oc<fixed-case>I</fixed-case>nfer: Document-level Natural Language Inference using Optimal Evidence Selection</title>
@@ -683,6 +732,7 @@
       <url hash="636639d0">2022.emnlp-main.51</url>
       <bibkey>mathur-etal-2022-docinfer</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.51</doi>
+      <video href="2022.emnlp-main.51.mp4"/>
     </paper>
     <paper id="52">
       <title><fixed-case>L</fixed-case>ight<fixed-case>EA</fixed-case>: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation</title>
@@ -695,6 +745,7 @@
       <url hash="33aabf75">2022.emnlp-main.52</url>
       <bibkey>mao-etal-2022-lightea</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.52</doi>
+      <video href="2022.emnlp-main.52.mp4"/>
     </paper>
     <paper id="53">
       <title>Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning</title>
@@ -713,6 +764,7 @@
       <url hash="03bb5a43">2022.emnlp-main.53</url>
       <bibkey>he-etal-2022-metric</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.53</doi>
+      <video href="2022.emnlp-main.53.mp4"/>
     </paper>
     <paper id="54">
       <title>Efficient Document Retrieval by End-to-End Refining and Quantizing <fixed-case>BERT</fixed-case> Embedding with Contrastive Product Quantization</title>
@@ -726,6 +778,7 @@
       <bibkey>qiu-etal-2022-efficient</bibkey>
       <attachment type="software" hash="1e90c61a">2022.emnlp-main.54.software.zip</attachment>
       <doi>10.18653/v1/2022.emnlp-main.54</doi>
+      <video href="2022.emnlp-main.54.mp4"/>
     </paper>
     <paper id="55">
       <title>Curriculum Knowledge Distillation for Emoji-supervised Cross-lingual Sentiment Analysis</title>
@@ -739,6 +792,7 @@
       <url hash="8578959d">2022.emnlp-main.55</url>
       <bibkey>zhang-etal-2022-curriculum</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.55</doi>
+      <video href="2022.emnlp-main.55.mp4"/>
     </paper>
     <paper id="56">
       <title>Correctable-<fixed-case>DST</fixed-case>: Mitigating Historical Context Mismatch between Training and Inference for Improved Dialogue State Tracking</title>
@@ -756,6 +810,7 @@
       <url hash="bd850fc7">2022.emnlp-main.56</url>
       <bibkey>xie-etal-2022-correctable</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.56</doi>
+      <video href="2022.emnlp-main.56.mp4"/>
     </paper>
     <paper id="57">
       <title><fixed-case>D</fixed-case>rop<fixed-case>M</fixed-case>ix: A Textual Data Augmentation Combining Dropout with Mixup</title>
@@ -769,6 +824,7 @@
       <url hash="4a5ab695">2022.emnlp-main.57</url>
       <bibkey>kong-etal-2022-dropmix</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.57</doi>
+      <video href="2022.emnlp-main.57.mp4"/>
     </paper>
     <paper id="58">
       <title>Cross-document Event Coreference Search: Task, Dataset and Modeling</title>
@@ -780,6 +836,7 @@
       <url hash="266b2c72">2022.emnlp-main.58</url>
       <bibkey>eirew-etal-2022-cross</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.58</doi>
+      <video href="2022.emnlp-main.58.mp4"/>
     </paper>
     <paper id="59">
       <title><fixed-case>VIRT</fixed-case>: Improving Representation-based Text Matching via Virtual Interaction</title>
@@ -797,6 +854,7 @@
       <url hash="fe02150a">2022.emnlp-main.59</url>
       <bibkey>li-etal-2022-virt</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.59</doi>
+      <video href="2022.emnlp-main.59.mp4"/>
     </paper>
     <paper id="60">
       <title><fixed-case>MAVEN</fixed-case>-<fixed-case>ERE</fixed-case>: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction</title>
@@ -817,6 +875,7 @@
       <url hash="78e6db1c">2022.emnlp-main.60</url>
       <bibkey>wang-etal-2022-maven</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.60</doi>
+      <video href="2022.emnlp-main.60.mp4"/>
     </paper>
     <paper id="61">
       <title>Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language Models</title>
@@ -829,6 +888,7 @@
       <url hash="02c8a8b3">2022.emnlp-main.61</url>
       <bibkey>mahapatra-etal-2022-entity</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.61</doi>
+      <video href="2022.emnlp-main.61.mp4"/>
     </paper>
     <paper id="62">
       <title>How Large Language Models are Transforming Machine-Paraphrase Plagiarism</title>
@@ -841,6 +901,7 @@
       <url hash="94f0a052">2022.emnlp-main.62</url>
       <bibkey>wahle-etal-2022-large</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.62</doi>
+      <video href="2022.emnlp-main.62.mp4"/>
     </paper>
     <paper id="63">
       <title><fixed-case>M</fixed-case>2<fixed-case>D</fixed-case>2: A Massively Multi-Domain Language Modeling Dataset</title>
@@ -853,6 +914,7 @@
       <url hash="d4326df9">2022.emnlp-main.63</url>
       <bibkey>reid-etal-2022-m2d2</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.63</doi>
+      <video href="2022.emnlp-main.63.mp4"/>
     </paper>
     <paper id="64">
       <title>“Will You Find These Shortcuts?” A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification</title>
@@ -866,6 +928,7 @@
       <url hash="02324fad">2022.emnlp-main.64</url>
       <bibkey>bastings-etal-2022-will</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.64</doi>
+      <video href="2022.emnlp-main.64.mp4"/>
     </paper>
     <paper id="65">
       <title>Information-Transport-based Policy for Simultaneous Translation</title>
@@ -876,6 +939,7 @@
       <url hash="6ea89705">2022.emnlp-main.65</url>
       <bibkey>zhang-feng-2022-information</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.65</doi>
+      <video href="2022.emnlp-main.65.mp4"/>
     </paper>
     <paper id="66">
       <title>Learning to Adapt to Low-Resource Paraphrase Generation</title>
@@ -890,6 +954,7 @@
       <url hash="3b8e3072">2022.emnlp-main.66</url>
       <bibkey>li-etal-2022-learning-adapt</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.66</doi>
+      <video href="2022.emnlp-main.66.mp4"/>
     </paper>
     <paper id="67">
       <title>A Distributional Lens for Multi-Aspect Controllable Text Generation</title>
@@ -904,6 +969,7 @@
       <url hash="a72b9fe2">2022.emnlp-main.67</url>
       <bibkey>gu-etal-2022-distributional</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.67</doi>
+      <video href="2022.emnlp-main.67.mp4"/>
     </paper>
     <paper id="68">
       <title><fixed-case>ELMER</fixed-case>: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generation</title>
@@ -917,6 +983,7 @@
       <url hash="d607efc4">2022.emnlp-main.68</url>
       <bibkey>li-etal-2022-elmer</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.68</doi>
+      <video href="2022.emnlp-main.68.mp4"/>
     </paper>
     <paper id="69">
       <title>Multilingual Relation Classification via Efficient and Effective Prompting</title>
@@ -928,6 +995,7 @@
       <url hash="f07651d6">2022.emnlp-main.69</url>
       <bibkey>chen-etal-2022-multilingual</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.69</doi>
+      <video href="2022.emnlp-main.69.mp4"/>
     </paper>
     <paper id="70">
       <title>Topic-Regularized Authorship Representation Learning</title>
@@ -940,6 +1008,7 @@
       <url hash="c8854bc7">2022.emnlp-main.70</url>
       <bibkey>sawatphol-etal-2022-topic</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.70</doi>
+      <video href="2022.emnlp-main.70.mp4"/>
     </paper>
     <paper id="71">
       <title>Fine-grained Contrastive Learning for Relation Extraction</title>
@@ -951,6 +1020,7 @@
       <url hash="fb758851">2022.emnlp-main.71</url>
       <bibkey>hogan-etal-2022-fine</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.71</doi>
+      <video href="2022.emnlp-main.71.mp4"/>
     </paper>
     <paper id="72">
       <title>Curriculum Prompt Learning with Self-Training for Abstractive Dialogue Summarization</title>
@@ -964,6 +1034,7 @@
       <url hash="dddbbe94">2022.emnlp-main.72</url>
       <bibkey>li-etal-2022-curriculum</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.72</doi>
+      <video href="2022.emnlp-main.72.mp4"/>
     </paper>
     <paper id="73">
       <title>Zero-Shot Text Classification with Self-Training</title>
@@ -978,6 +1049,7 @@
       <url hash="80340f9f">2022.emnlp-main.73</url>
       <bibkey>gera-etal-2022-zero</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.73</doi>
+      <video href="2022.emnlp-main.73.mp4"/>
     </paper>
     <paper id="74">
       <title>Deconfounding Legal Judgment Prediction for <fixed-case>E</fixed-case>uropean Court of Human Rights Cases Towards Better Alignment with Experts</title>
@@ -990,6 +1062,7 @@
       <url hash="6f45760b">2022.emnlp-main.74</url>
       <bibkey>santosh-etal-2022-deconfounding</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.74</doi>
+      <video href="2022.emnlp-main.74.mp4"/>
     </paper>
     <paper id="75">
       <title><fixed-case>SQ</fixed-case>u<fixed-case>ALITY</fixed-case>: Building a Long-Document Summarization Dataset the Hard Way</title>
@@ -1004,6 +1077,7 @@
       <attachment type="dataset" hash="367c3b28">2022.emnlp-main.75.dataset.zip</attachment>
       <bibkey>wang-etal-2022-squality</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.75</doi>
+      <video href="2022.emnlp-main.75.mp4"/>
     </paper>
     <paper id="76">
       <title><fixed-case>M</fixed-case>eta<fixed-case>ASSIST</fixed-case>: Robust Dialogue State Tracking with Meta Learning</title>
@@ -1018,6 +1092,7 @@
       <url hash="f818695f">2022.emnlp-main.76</url>
       <bibkey>ye-etal-2022-metaassist</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.76</doi>
+      <video href="2022.emnlp-main.76.mp4"/>
     </paper>
     <paper id="77">
       <title>Multilingual Machine Translation with Hyper-Adapters</title>
@@ -1031,6 +1106,7 @@
       <bibkey>baziotis-etal-2022-multilingual</bibkey>
       <attachment type="data" hash="f937d6d3">2022.emnlp-main.77.data.zip</attachment>
       <doi>10.18653/v1/2022.emnlp-main.77</doi>
+      <video href="2022.emnlp-main.77.mp4"/>
     </paper>
     <paper id="78">
       <title><fixed-case>Z</fixed-case>-<fixed-case>L</fixed-case>a<fixed-case>VI</fixed-case>: Zero-Shot Language Solver Fueled by Visual Imagination</title>
@@ -1045,6 +1121,7 @@
       <url hash="640e1c1d">2022.emnlp-main.78</url>
       <bibkey>yang-etal-2022-z</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.78</doi>
+      <video href="2022.emnlp-main.78.mp4"/>
     </paper>
     <paper id="79">
       <title>Using Commonsense Knowledge to Answer Why-Questions</title>
@@ -1060,6 +1137,7 @@
       <url hash="32309f50">2022.emnlp-main.79</url>
       <bibkey>lal-etal-2022-using</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.79</doi>
+      <video href="2022.emnlp-main.79.mp4"/>
     </paper>
     <paper id="80">
       <title>Affective Idiosyncratic Responses to Music</title>
@@ -1073,6 +1151,7 @@
       <url hash="e1f3528b">2022.emnlp-main.80</url>
       <bibkey>ch-wang-etal-2022-affective</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.80</doi>
+      <video href="2022.emnlp-main.80.mp4"/>
     </paper>
     <paper id="81">
       <title>Successive Prompting for Decomposing Complex Questions</title>
@@ -1085,6 +1164,7 @@
       <url hash="67f49081">2022.emnlp-main.81</url>
       <bibkey>dua-etal-2022-successive</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.81</doi>
+      <video href="2022.emnlp-main.81.mp4"/>
     </paper>
     <paper id="82">
       <title>Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations</title>
@@ -1101,6 +1181,7 @@
       <attachment type="software" hash="f291a7f2">2022.emnlp-main.82.software.zip</attachment>
       <bibkey>jung-etal-2022-maieutic</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.82</doi>
+      <video href="2022.emnlp-main.82.mp4"/>
     </paper>
     <paper id="83">
       <title><fixed-case>DANLI</fixed-case>: Deliberative Agent for Following Natural Language Instructions</title>
@@ -1118,6 +1199,7 @@
       <url hash="932681ae">2022.emnlp-main.83</url>
       <bibkey>zhang-etal-2022-danli</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.83</doi>
+      <video href="2022.emnlp-main.83.mp4"/>
     </paper>
     <paper id="84">
       <title>Tracing Semantic Variation in Slang</title>
@@ -1130,6 +1212,7 @@
       <attachment type="dataset" hash="8ed113aa">2022.emnlp-main.84.dataset.zip</attachment>
       <bibkey>sun-xu-2022-tracing</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.84</doi>
+      <video href="2022.emnlp-main.84.mp4"/>
     </paper>
     <paper id="85">
       <title>Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning</title>
@@ -1144,6 +1227,7 @@
       <url hash="e70c7359">2022.emnlp-main.85</url>
       <bibkey>an-etal-2022-fine</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.85</doi>
+      <video href="2022.emnlp-main.85.mp4"/>
     </paper>
     <paper id="86">
       <title><fixed-case>PLM</fixed-case>-based World Models for Text-based Games</title>
@@ -1158,6 +1242,7 @@
       <attachment type="software" hash="dae6fb3a">2022.emnlp-main.86.software.zip</attachment>
       <bibkey>kim-etal-2022-plm</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.86</doi>
+      <video href="2022.emnlp-main.86.mp4"/>
     </paper>
     <paper id="87">
       <title>Prompt-Based Meta-Learning For Few-shot Text Classification</title>
@@ -1171,6 +1256,7 @@
       <bibkey>zhang-etal-2022-prompt-based</bibkey>
       <attachment type="data" hash="7825ad69">2022.emnlp-main.87.data.zip</attachment>
       <doi>10.18653/v1/2022.emnlp-main.87</doi>
+      <video href="2022.emnlp-main.87.mp4"/>
     </paper>
     <paper id="88">
       <title>How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?</title>
@@ -1185,6 +1271,7 @@
       <bibkey>bansal-etal-2022-well</bibkey>
       <attachment type="software" hash="69edf3d2">2022.emnlp-main.88.software.zip</attachment>
       <doi>10.18653/v1/2022.emnlp-main.88</doi>
+      <video href="2022.emnlp-main.88.mp4"/>
     </paper>
     <paper id="89">
       <title>Geographic Citation Gaps in <fixed-case>NLP</fixed-case> Research</title>
@@ -1197,6 +1284,7 @@
       <url hash="4e4a6aa2">2022.emnlp-main.89</url>
       <bibkey>rungta-etal-2022-geographic</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.89</doi>
+      <video href="2022.emnlp-main.89.mp4"/>
     </paper>
     <paper id="90">
       <title>Language Models of Code are Few-Shot Commonsense Learners</title>
@@ -1210,6 +1298,7 @@
       <url hash="183fef3c">2022.emnlp-main.90</url>
       <bibkey>madaan-etal-2022-language</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.90</doi>
+      <video href="2022.emnlp-main.90.mp4"/>
     </paper>
     <paper id="91">
       <title>Numerical Optimizations for Weighted Low-rank Estimation on Language Models</title>
@@ -1225,6 +1314,7 @@
       <attachment type="note" hash="9b708dc9">2022.emnlp-main.91.note.pdf</attachment>
       <bibkey>hua-etal-2022-numerical</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.91</doi>
+      <video href="2022.emnlp-main.91.mp4"/>
     </paper>
     <paper id="92">
       <title>Generative Multi-hop Retrieval</title>
@@ -1237,6 +1327,7 @@
       <url hash="e04357d2">2022.emnlp-main.92</url>
       <bibkey>lee-etal-2022-generative</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.92</doi>
+      <video href="2022.emnlp-main.92.mp4"/>
     </paper>
     <paper id="93">
       <title>Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation</title>
@@ -1251,6 +1342,7 @@
       <url hash="e7111f17">2022.emnlp-main.93</url>
       <bibkey>zhao-etal-2022-visual</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.93</doi>
+      <video href="2022.emnlp-main.93.mp4"/>
     </paper>
     <paper id="94">
       <title><fixed-case>M</fixed-case>3: A Multi-View Fusion and Multi-Decoding Network for Multi-Document Reading Comprehension</title>
@@ -1263,6 +1355,7 @@
       <url hash="e445eeaf">2022.emnlp-main.94</url>
       <bibkey>wen-etal-2022-m3</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.94</doi>
+      <video href="2022.emnlp-main.94.mp4"/>
     </paper>
     <paper id="95">
       <title><fixed-case>COCO</fixed-case>-<fixed-case>DR</fixed-case>: Combating the Distribution Shift in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning</title>
@@ -1276,6 +1369,7 @@
       <url hash="e8500b0e">2022.emnlp-main.95</url>
       <bibkey>yu-etal-2022-coco</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.95</doi>
+      <video href="2022.emnlp-main.95.mp4"/>
     </paper>
     <paper id="96">
       <title>Language Model Pre-Training with Sparse Latent Typing</title>
@@ -1290,6 +1384,7 @@
       <url hash="76ba6606">2022.emnlp-main.96</url>
       <bibkey>ren-etal-2022-language</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.96</doi>
+      <video href="2022.emnlp-main.96.mp4"/>
     </paper>
     <paper id="97">
       <title>On the Transformation of Latent Space in Fine-Tuned <fixed-case>NLP</fixed-case> Models</title>
@@ -1302,6 +1397,7 @@
       <url hash="3598d731">2022.emnlp-main.97</url>
       <bibkey>durrani-etal-2022-transformation</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.97</doi>
+      <video href="2022.emnlp-main.97.mp4"/>
     </paper>
     <paper id="98">
       <title>Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for <fixed-case>OOD</fixed-case> Intent Discovery</title>
@@ -1317,6 +1413,7 @@
       <url hash="d42a86a5">2022.emnlp-main.98</url>
       <bibkey>mou-etal-2022-watch</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.98</doi>
+      <video href="2022.emnlp-main.98.mp4"/>
     </paper>
     <paper id="99">
       <title>Extracted <fixed-case>BERT</fixed-case> Model Leaks More Information than You Think!</title>
@@ -1329,6 +1426,7 @@
       <url hash="1d155977">2022.emnlp-main.99</url>
       <bibkey>he-etal-2022-extracted</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.99</doi>
+      <video href="2022.emnlp-main.99.mp4"/>
     </paper>
     <paper id="100">
       <title>Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?</title>
@@ -1342,6 +1440,7 @@
       <url hash="71702b8e">2022.emnlp-main.100</url>
       <bibkey>nikolaus-etal-2022-vision</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.100</doi>
+      <video href="2022.emnlp-main.100.mp4"/>
     </paper>
     <paper id="101">
       <title>A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference</title>
@@ -1352,6 +1451,7 @@
       <url hash="fddb6eb4">2022.emnlp-main.101</url>
       <bibkey>zaman-belinkov-2022-multilingual</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.101</doi>
+      <video href="2022.emnlp-main.101.mp4"/>
     </paper>
     <paper id="102">
       <title>Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging</title>
@@ -1365,6 +1465,7 @@
       <url hash="7a70221e">2022.emnlp-main.102</url>
       <bibkey>imanigooghari-etal-2022-graph</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.102</doi>
+      <video href="2022.emnlp-main.102.mp4"/>
     </paper>
     <paper id="103">
       <title><fixed-case>S</fixed-case>ubevent<fixed-case>W</fixed-case>riter: Iterative Sub-event Sequence Generation with Coherence Controller</title>
@@ -1379,6 +1480,7 @@
       <url hash="6e399e9f">2022.emnlp-main.103</url>
       <bibkey>wang-etal-2022-subeventwriter</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.103</doi>
+      <video href="2022.emnlp-main.103.mp4"/>
     </paper>
     <paper id="104">
       <title>Infinite <fixed-case>SCAN</fixed-case>: An Infinite Model of Diachronic Semantic Change</title>
@@ -1392,6 +1494,7 @@
       <url hash="f9f1a4ae">2022.emnlp-main.104</url>
       <bibkey>inoue-etal-2022-infinite</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.104</doi>
+      <video href="2022.emnlp-main.104.mp4"/>
     </paper>
     <paper id="105">
       <title>Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization</title>
@@ -1405,6 +1508,7 @@
       <attachment type="software" hash="78e5aa13">2022.emnlp-main.105.software.zip</attachment>
       <bibkey>gu-etal-2022-learning</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.105</doi>
+      <video href="2022.emnlp-main.105.mp4"/>
     </paper>
     <paper id="106">
       <title>Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues</title>
@@ -1417,6 +1521,7 @@
       <url hash="8c45e579">2022.emnlp-main.106</url>
       <bibkey>ou-etal-2022-counterfactual</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.106</doi>
+      <video href="2022.emnlp-main.106.mp4"/>
     </paper>
     <paper id="107">
       <title><fixed-case>SQUIRE</fixed-case>: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning</title>
@@ -1432,6 +1537,7 @@
       <url hash="a4b1b04f">2022.emnlp-main.107</url>
       <bibkey>bai-etal-2022-squire</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.107</doi>
+      <video href="2022.emnlp-main.107.mp4"/>
     </paper>
     <paper id="108">
       <title><fixed-case>S</fixed-case>peech<fixed-case>UT</fixed-case>: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training</title>
@@ -1447,6 +1553,7 @@
       <url hash="ff26bad5">2022.emnlp-main.108</url>
       <bibkey>zhang-etal-2022-speechut</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.108</doi>
+      <video href="2022.emnlp-main.108.mp4"/>
     </paper>
     <paper id="109">
       <title>Learning Label Modular Prompts for Text Classification in the Wild</title>
@@ -1459,6 +1566,7 @@
       <url hash="6be77547">2022.emnlp-main.109</url>
       <bibkey>chen-etal-2022-learning-label</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.109</doi>
+      <video href="2022.emnlp-main.109.mp4"/>
     </paper>
     <paper id="110">
       <title>Unbiased and Efficient Sampling of Dependency Trees</title>
@@ -1468,6 +1576,7 @@
       <url hash="dd05b4fc">2022.emnlp-main.110</url>
       <bibkey>stanojevic-2022-unbiased</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.110</doi>
+      <video href="2022.emnlp-main.110.mp4"/>
     </paper>
     <paper id="111">
       <title>Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions</title>
@@ -1480,6 +1589,7 @@
       <attachment type="software" hash="16a54e35">2022.emnlp-main.111.software.zip</attachment>
       <bibkey>gu-etal-2022-continual</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.111</doi>
+      <video href="2022.emnlp-main.111.mp4"/>
     </paper>
     <paper id="112">
       <title><fixed-case>COST</fixed-case>-<fixed-case>EFF</fixed-case>: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models</title>
@@ -1495,6 +1605,7 @@
       <attachment type="software" hash="2e718e0d">2022.emnlp-main.112.software.zip</attachment>
       <bibkey>shen-etal-2022-cost</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.112</doi>
+      <video href="2022.emnlp-main.112.mp4"/>
     </paper>
     <paper id="113">
       <title>Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction</title>
@@ -1509,6 +1620,7 @@
       <url hash="a41df3b9">2022.emnlp-main.113</url>
       <bibkey>wan-etal-2022-rescue</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.113</doi>
+      <video href="2022.emnlp-main.113.mp4"/>
     </paper>
     <paper id="114">
       <title><fixed-case>S</fixed-case>tory<fixed-case>ER</fixed-case>: Automatic Story Evaluation via Ranking, Rating and Reasoning</title>
@@ -1522,6 +1634,7 @@
       <url hash="89deb681">2022.emnlp-main.114</url>
       <bibkey>chen-etal-2022-storyer</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.114</doi>
+      <video href="2022.emnlp-main.114.mp4"/>
     </paper>
     <paper id="115">
       <title>Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference</title>
@@ -1538,6 +1651,7 @@
       <url hash="b1d50d7a">2022.emnlp-main.115</url>
       <bibkey>mitchell-etal-2022-enhancing</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.115</doi>
+      <video href="2022.emnlp-main.115.mp4"/>
     </paper>
     <paper id="116">
       <title>Robustness of Demonstration-based Learning Under Limited Data Scenario</title>
@@ -1551,6 +1665,7 @@
       <attachment type="software" hash="c1a3efba">2022.emnlp-main.116.software.zip</attachment>
       <bibkey>zhang-etal-2022-robustness</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.116</doi>
+      <video href="2022.emnlp-main.116.mp4"/>
     </paper>
     <paper id="117">
       <title>Modeling Information Change in Science Communication with Semantically Matched Paraphrases</title>
@@ -1563,6 +1678,7 @@
       <url hash="03f3e521">2022.emnlp-main.117</url>
       <bibkey>wright-etal-2022-modeling</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.117</doi>
+      <video href="2022.emnlp-main.117.mp4"/>
     </paper>
     <paper id="118">
       <title>Word Order Matters When You Increase Masking</title>
@@ -1574,6 +1690,7 @@
       <url hash="f7514029">2022.emnlp-main.118</url>
       <bibkey>lasri-etal-2022-word</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.118</doi>
+      <video href="2022.emnlp-main.118.mp4"/>
     </paper>
     <paper id="119">
       <title>An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models</title>
@@ -1587,6 +1704,7 @@
       <url hash="d4137642">2022.emnlp-main.119</url>
       <bibkey>mireshghallah-etal-2022-empirical</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.119</doi>
+      <video href="2022.emnlp-main.119.mp4"/>
     </paper>
     <paper id="120">
       <title>Style Transfer as Data Augmentation: A Case Study on Named Entity Recognition</title>
@@ -1598,6 +1716,7 @@
       <url hash="2e99afa6">2022.emnlp-main.120</url>
       <bibkey>chen-etal-2022-style</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.120</doi>
+      <video href="2022.emnlp-main.120.mp4"/>
     </paper>
     <paper id="121">
       <title>Linguistic Corpus Annotation for Automatic Text Simplification Evaluation</title>
@@ -1614,6 +1733,7 @@
       <url hash="29fba2f9">2022.emnlp-main.121</url>
       <bibkey>cardon-etal-2022-linguistic</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.121</doi>
+      <video href="2022.emnlp-main.121.mp4"/>
     </paper>
     <paper id="122">
       <title>Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs</title>
@@ -1627,6 +1747,7 @@
       <attachment type="dataset" hash="7e27ad98">2022.emnlp-main.122.dataset.zip</attachment>
       <bibkey>ding-etal-2022-semantic</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.122</doi>
+      <video href="2022.emnlp-main.122.mp4"/>
     </paper>
     <paper id="123">
       <title>There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning</title>
@@ -1639,6 +1760,7 @@
       <url hash="127034dc">2022.emnlp-main.123</url>
       <bibkey>zhao-etal-2022-standard</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.123</doi>
+      <video href="2022.emnlp-main.123.mp4"/>
     </paper>
     <paper id="124">
       <title>Stop Measuring Calibration When Humans Disagree</title>
@@ -1651,6 +1773,7 @@
       <url hash="8f8c6924">2022.emnlp-main.124</url>
       <bibkey>baan-etal-2022-stop</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.124</doi>
+      <video href="2022.emnlp-main.124.mp4"/>
     </paper>
     <paper id="125">
       <title>Improving compositional generalization for multi-step quantitative reasoning in question answering</title>
@@ -1663,6 +1786,7 @@
       <url hash="a264bde6">2022.emnlp-main.125</url>
       <bibkey>nourbakhsh-etal-2022-improving</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.125</doi>
+      <video href="2022.emnlp-main.125.mp4"/>
     </paper>
     <paper id="126">
       <title>A Comprehensive Comparison of Neural Networks as Cognitive Models of Inflection</title>
@@ -1674,6 +1798,7 @@
       <url hash="f779b22f">2022.emnlp-main.126</url>
       <bibkey>wiemerslage-etal-2022-comprehensive</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.126</doi>
+      <video href="2022.emnlp-main.126.mp4"/>
     </paper>
     <paper id="127">
       <title>Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?</title>
@@ -1684,6 +1809,7 @@
       <url hash="947b306c">2022.emnlp-main.127</url>
       <bibkey>pramanick-sarkar-2022-visual</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.127</doi>
+      <video href="2022.emnlp-main.127.mp4"/>
     </paper>
     <paper id="128">
       <title><fixed-case>A</fixed-case>fro<fixed-case>LID</fixed-case>: A Neural Language Identification Tool for <fixed-case>A</fixed-case>frican Languages</title>
@@ -1696,6 +1822,7 @@
       <url hash="c61bbfe4">2022.emnlp-main.128</url>
       <bibkey>adebara-etal-2022-afrolid</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.128</doi>
+      <video href="2022.emnlp-main.128.mp4"/>
     </paper>
     <paper id="129">
       <title><fixed-case>E</fixed-case>v<fixed-case>E</fixed-case>nt<fixed-case>S</fixed-case> <fixed-case>R</fixed-case>ea<fixed-case>LM</fixed-case>: Event Reasoning of Entity States via Language Models</title>
@@ -1708,6 +1835,7 @@
       <url hash="9e374e11">2022.emnlp-main.129</url>
       <bibkey>spiliopoulou-etal-2022-events</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.129</doi>
+      <video href="2022.emnlp-main.129.mp4"/>
     </paper>
     <paper id="130">
       <title>Large language models are few-shot clinical information extractors</title>
@@ -1721,6 +1849,7 @@
       <url hash="d5a129e3">2022.emnlp-main.130</url>
       <bibkey>agrawal-etal-2022-large</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.130</doi>
+      <video href="2022.emnlp-main.130.mp4"/>
     </paper>
     <paper id="131">
       <title>Towards a Unified Multi-Dimensional Evaluator for Text Generation</title>
@@ -1738,6 +1867,7 @@
       <url hash="374acf24">2022.emnlp-main.131</url>
       <bibkey>zhong-etal-2022-towards</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.131</doi>
+      <video href="2022.emnlp-main.131.mp4"/>
     </paper>
     <paper id="132">
       <title><fixed-case>G</fixed-case>eo<fixed-case>MLAMA</fixed-case>: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models</title>
@@ -1751,6 +1881,7 @@
       <url hash="73c94419">2022.emnlp-main.132</url>
       <bibkey>yin-etal-2022-geomlama</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.132</doi>
+      <video href="2022.emnlp-main.132.mp4"/>
     </paper>
     <paper id="133">
       <title>The (Undesired) Attenuation of Human Biases by Multilinguality</title>
@@ -1761,6 +1892,7 @@
       <url hash="788d3b7c">2022.emnlp-main.133</url>
       <bibkey>espana-bonet-barron-cedeno-2022-undesired</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.133</doi>
+      <video href="2022.emnlp-main.133.mp4"/>
     </paper>
     <paper id="134">
       <title>Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning</title>
@@ -1772,6 +1904,7 @@
       <url hash="d01f33ca">2022.emnlp-main.134</url>
       <bibkey>tafjord-etal-2022-entailer</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.134</doi>
+      <video href="2022.emnlp-main.134.mp4"/>
     </paper>
     <paper id="135">
       <title>Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets</title>
@@ -1784,6 +1917,7 @@
       <url hash="fc3ff597">2022.emnlp-main.135</url>
       <bibkey>laban-etal-2022-near</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.135</doi>
+      <video href="2022.emnlp-main.135.mp4"/>
     </paper>
     <paper id="136">
       <title><fixed-case>T</fixed-case>o<fixed-case>K</fixed-case>en: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection</title>
@@ -1802,6 +1936,7 @@
       <url hash="d97f8856">2022.emnlp-main.136</url>
       <bibkey>alkhamissi-etal-2022-token</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.136</doi>
+      <video href="2022.emnlp-main.136.mp4"/>
     </paper>
     <paper id="137">
       <title>Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations</title>
@@ -1814,6 +1949,7 @@
       <url hash="1912f05a">2022.emnlp-main.137</url>
       <bibkey>saha-etal-2022-hard</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.137</doi>
+      <video href="2022.emnlp-main.137.mp4"/>
     </paper>
     <paper id="138">
       <title>Stanceosaurus: Classifying Stance Towards Multicultural Misinformation</title>
@@ -1828,6 +1964,7 @@
       <attachment type="software" hash="65ceadd9">2022.emnlp-main.138.software.zip</attachment>
       <bibkey>zheng-etal-2022-stanceosaurus</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.138</doi>
+      <video href="2022.emnlp-main.138.mp4"/>
     </paper>
     <paper id="139">
       <title>Gendered Mental Health Stigma in Masked Language Models</title>
@@ -1843,6 +1980,7 @@
       <url hash="8f93f102">2022.emnlp-main.139</url>
       <bibkey>lin-etal-2022-gendered</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.139</doi>
+      <video href="2022.emnlp-main.139.mp4"/>
     </paper>
     <paper id="140">
       <title>Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization</title>
@@ -1856,6 +1994,7 @@
       <url hash="a16bd232">2022.emnlp-main.140</url>
       <bibkey>yadav-etal-2022-efficient</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.140</doi>
+      <video href="2022.emnlp-main.140.mp4"/>
     </paper>
     <paper id="141">
       <title>Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models</title>
@@ -1867,6 +2006,7 @@
       <url hash="f6b34817">2022.emnlp-main.141</url>
       <bibkey>suzgun-etal-2022-prompt</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.141</doi>
+      <video href="2022.emnlp-main.141.mp4"/>
     </paper>
     <paper id="142">
       <title>Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts</title>
@@ -1879,6 +2019,7 @@
       <url hash="52ddda36">2022.emnlp-main.142</url>
       <bibkey>zhou-etal-2022-learning-decompose</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.142</doi>
+      <video href="2022.emnlp-main.142.mp4"/>
     </paper>
     <paper id="143">
       <title>Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality</title>
@@ -1892,6 +2033,7 @@
       <url hash="f60032d7">2022.emnlp-main.143</url>
       <bibkey>diwan-etal-2022-winoground</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.143</doi>
+      <video href="2022.emnlp-main.143.mp4"/>
     </paper>
     <paper id="144">
       <title>Gradient-based Constrained Sampling from Language Models</title>
@@ -1903,6 +2045,7 @@
       <url hash="dfc802a7">2022.emnlp-main.144</url>
       <bibkey>kumar-etal-2022-gradient</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.144</doi>
+      <video href="2022.emnlp-main.144.mp4"/>
     </paper>
     <paper id="145">
       <title><fixed-case>T</fixed-case>a<fixed-case>C</fixed-case>ube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data</title>
@@ -1918,6 +2061,7 @@
       <url hash="999261d2">2022.emnlp-main.145</url>
       <bibkey>zhou-etal-2022-tacube</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.145</doi>
+      <video href="2022.emnlp-main.145.mp4"/>
     </paper>
     <paper id="146">
       <title>Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence</title>
@@ -1931,6 +2075,7 @@
       <attachment type="dataset" hash="994f6f03">2022.emnlp-main.146.dataset.zip</attachment>
       <bibkey>chen-etal-2022-rich</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.146</doi>
+      <video href="2022.emnlp-main.146.mp4"/>
     </paper>
     <paper id="147">
       <title><fixed-case>QA</fixed-case> Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation</title>
@@ -1944,6 +2089,7 @@
       <url hash="b70254bd">2022.emnlp-main.147</url>
       <bibkey>yue-etal-2022-qa</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.147</doi>
+      <video href="2022.emnlp-main.147.mp4"/>
     </paper>
     <paper id="148">
       <title>When <fixed-case>FLUE</fixed-case> Meets <fixed-case>FLANG</fixed-case>: Benchmarks and Large Pretrained Language Model for Financial Domain</title>
@@ -1962,6 +2108,7 @@
       <url hash="e82d0822">2022.emnlp-main.148</url>
       <bibkey>shah-etal-2022-flue</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.148</doi>
+      <video href="2022.emnlp-main.148.mp4"/>
     </paper>
     <paper id="149">
       <title>Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer</title>
@@ -1977,6 +2124,7 @@
       <url hash="221c2a4a">2022.emnlp-main.149</url>
       <bibkey>jiang-etal-2022-retrieval</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.149</doi>
+      <video href="2022.emnlp-main.149.mp4"/>
     </paper>
     <paper id="150">
       <title>Reproducibility in Computational Linguistics: Is Source Code Enough?</title>
@@ -1989,6 +2137,7 @@
       <attachment type="software" hash="78b06bd9">2022.emnlp-main.150.software.zip</attachment>
       <bibkey>arvan-etal-2022-reproducibility-computational</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.150</doi>
+      <video href="2022.emnlp-main.150.mp4"/>
     </paper>
     <paper id="151">
       <title>Generating Information-Seeking Conversations from Unlabeled Documents</title>
@@ -2001,6 +2150,7 @@
       <url hash="f9e8146a">2022.emnlp-main.151</url>
       <bibkey>kim-etal-2022-generating</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.151</doi>
+      <video href="2022.emnlp-main.151.mp4"/>
     </paper>
     <paper id="152">
       <title>Distill The Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation</title>
@@ -2012,6 +2162,7 @@
       <url hash="8f298266">2022.emnlp-main.152</url>
       <bibkey>peng-etal-2022-distill</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.152</doi>
+      <video href="2022.emnlp-main.152.mp4"/>
     </paper>
     <paper id="153">
       <title>A Multifaceted Framework to Evaluate Evasion, Content Preservation, and Misattribution in Authorship Obfuscation Techniques</title>
@@ -2024,6 +2175,7 @@
       <url hash="99f627e3">2022.emnlp-main.153</url>
       <bibkey>altakrori-etal-2022-multifaceted</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.153</doi>
+      <video href="2022.emnlp-main.153.mp4"/>
     </paper>
     <paper id="154">
       <title><fixed-case>S</fixed-case>afe<fixed-case>T</fixed-case>ext: A Benchmark for Exploring Physical Safety in Language Models</title>
@@ -2039,6 +2191,7 @@
       <url hash="451f3c6d">2022.emnlp-main.154</url>
       <bibkey>levy-etal-2022-safetext</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.154</doi>
+      <video href="2022.emnlp-main.154.mp4"/>
     </paper>
     <paper id="155">
       <title>Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations</title>
@@ -2055,6 +2208,7 @@
       <url hash="38442f87">2022.emnlp-main.155</url>
       <bibkey>yoo-etal-2022-ground</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.155</doi>
+      <video href="2022.emnlp-main.155.mp4"/>
     </paper>
     <paper id="156">
       <title>D4: a <fixed-case>C</fixed-case>hinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat</title>
@@ -2072,6 +2226,7 @@
       <attachment type="note" hash="227c9cc6">2022.emnlp-main.156.note.pdf</attachment>
       <bibkey>yao-etal-2022-d4</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.156</doi>
+      <video href="2022.emnlp-main.156.mp4"/>
     </paper>
     <paper id="157">
       <title>Exploiting domain-slot related keywords description for Few-Shot Cross-Domain Dialogue State Tracking</title>
@@ -2088,6 +2243,7 @@
       <url hash="2788b759">2022.emnlp-main.157</url>
       <bibkey>qixiang-etal-2022-exploiting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.157</doi>
+      <video href="2022.emnlp-main.157.mp4"/>
     </paper>
     <paper id="158">
       <title><fixed-case>C</fixed-case>o<fixed-case>C</fixed-case>oa: An Encoder-Decoder Model for Controllable Code-switched Generation</title>
@@ -2101,6 +2257,7 @@
       <url hash="0fe861dc">2022.emnlp-main.158</url>
       <bibkey>mondal-etal-2022-cocoa</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.158</doi>
+      <video href="2022.emnlp-main.158.mp4"/>
     </paper>
     <paper id="159">
       <title>Towards Climate Awareness in <fixed-case>NLP</fixed-case> Research</title>
@@ -2114,6 +2271,7 @@
       <url hash="abe39f47">2022.emnlp-main.159</url>
       <bibkey>hershcovich-etal-2022-towards</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.159</doi>
+      <video href="2022.emnlp-main.159.mp4"/>
     </paper>
     <paper id="160">
       <title>Navigating Connected Memories with a Task-oriented Dialog System</title>
@@ -2126,6 +2284,7 @@
       <url hash="db7f2cb6">2022.emnlp-main.160</url>
       <bibkey>kottur-etal-2022-navigating</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.160</doi>
+      <video href="2022.emnlp-main.160.mp4"/>
     </paper>
     <paper id="161">
       <title>Language Model Decomposition: Quantifying the Dependency and Correlation of Language Models</title>
@@ -2135,6 +2294,7 @@
       <url hash="935936f0">2022.emnlp-main.161</url>
       <bibkey>zhang-2022-language</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.161</doi>
+      <video href="2022.emnlp-main.161.mp4"/>
     </paper>
     <paper id="162">
       <title><fixed-case>S</fixed-case>yn<fixed-case>GEC</fixed-case>: Syntax-Enhanced Grammatical Error Correction with a Tailored <fixed-case>GEC</fixed-case>-Oriented Parser</title>
@@ -2149,6 +2309,7 @@
       <url hash="9ba09ce2">2022.emnlp-main.162</url>
       <bibkey>zhang-etal-2022-syngec</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.162</doi>
+      <video href="2022.emnlp-main.162.mp4"/>
     </paper>
     <paper id="163">
       <title>Varifocal Question Generation for Fact-checking</title>
@@ -2160,6 +2321,7 @@
       <url hash="5351d347">2022.emnlp-main.163</url>
       <bibkey>ousidhoum-etal-2022-varifocal</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.163</doi>
+      <video href="2022.emnlp-main.163.mp4"/>
     </paper>
     <paper id="164">
       <title>Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport</title>
@@ -2173,6 +2335,7 @@
       <url hash="3cd191a0">2022.emnlp-main.164</url>
       <bibkey>marchisio-etal-2022-bilingual</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.164</doi>
+      <video href="2022.emnlp-main.164.mp4"/>
     </paper>
     <paper id="165">
       <title>Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection</title>
@@ -2189,6 +2352,7 @@
       <url hash="e792df3d">2022.emnlp-main.165</url>
       <bibkey>gururangan-etal-2022-whose</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.165</doi>
+      <video href="2022.emnlp-main.165.mp4"/>
     </paper>
     <paper id="166">
       <title><fixed-case>C</fixed-case>on<fixed-case>R</fixed-case>eader: Exploring Implicit Relations in Contracts for Contract Clause Extraction</title>
@@ -2203,6 +2367,7 @@
       <url hash="2d01650a">2022.emnlp-main.166</url>
       <bibkey>xu-etal-2022-conreader</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.166</doi>
+      <video href="2022.emnlp-main.166.mp4"/>
     </paper>
     <paper id="167">
       <title>Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual <fixed-case>NLU</fixed-case></title>
@@ -2214,6 +2379,7 @@
       <url hash="29665a19">2022.emnlp-main.167</url>
       <bibkey>christopoulou-etal-2022-training</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.167</doi>
+      <video href="2022.emnlp-main.167.mp4"/>
     </paper>
     <paper id="168">
       <title>Revisiting Parameter-Efficient Tuning: Are We Really There Yet?</title>
@@ -2226,6 +2392,7 @@
       <url hash="2f627fe0">2022.emnlp-main.168</url>
       <bibkey>chen-etal-2022-revisiting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.168</doi>
+      <video href="2022.emnlp-main.168.mp4"/>
     </paper>
     <paper id="169">
       <title>Transfer Learning from Semantic Role Labeling to Event Argument Extraction with Template-based Slot Querying</title>
@@ -2237,6 +2404,7 @@
       <url hash="be5053f1">2022.emnlp-main.169</url>
       <bibkey>zhang-etal-2022-transfer</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.169</doi>
+      <video href="2022.emnlp-main.169.mp4"/>
     </paper>
     <paper id="170">
       <title>Calibrating Zero-shot Cross-lingual (Un-)structured Predictions</title>
@@ -2248,6 +2416,7 @@
       <url hash="063d3780">2022.emnlp-main.170</url>
       <bibkey>jiang-etal-2022-calibrating</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.170</doi>
+      <video href="2022.emnlp-main.170.mp4"/>
     </paper>
     <paper id="171">
       <title><fixed-case>PRINCE</fixed-case>: Prefix-Masked Decoding for Knowledge Enhanced Sequence-to-Sequence Pre-Training</title>
@@ -2262,6 +2431,7 @@
       <attachment type="software" hash="7dc4ad63">2022.emnlp-main.171.software.zip</attachment>
       <bibkey>xu-etal-2022-prince</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.171</doi>
+      <video href="2022.emnlp-main.171.mp4"/>
     </paper>
     <paper id="172">
       <title>How Far are We from Robust Long Abstractive Summarization?</title>
@@ -2276,6 +2446,7 @@
       <attachment type="dataset" hash="91c16127">2022.emnlp-main.172.dataset.zip</attachment>
       <bibkey>koh-etal-2022-far</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.172</doi>
+      <video href="2022.emnlp-main.172.mp4"/>
     </paper>
     <paper id="173">
       <title>Measuring Context-Word Biases in Lexical Semantic Datasets</title>
@@ -2288,6 +2459,7 @@
       <bibkey>liu-etal-2022-measuring</bibkey>
       <attachment type="software" hash="d5f0189d">2022.emnlp-main.173.software.zip</attachment>
       <doi>10.18653/v1/2022.emnlp-main.173</doi>
+      <video href="2022.emnlp-main.173.mp4"/>
     </paper>
     <paper id="174">
       <title>Iteratively Prompt Pre-trained Language Models for Chain of Thought</title>
@@ -2299,6 +2471,7 @@
       <url hash="c73ae468">2022.emnlp-main.174</url>
       <bibkey>wang-etal-2022-iteratively</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.174</doi>
+      <video href="2022.emnlp-main.174.mp4"/>
     </paper>
     <paper id="175">
       <title>Unobserved Local Structures Make Compositional Generalization Hard</title>
@@ -2310,6 +2483,7 @@
       <url hash="2f53e401">2022.emnlp-main.175</url>
       <bibkey>bogin-etal-2022-unobserved</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.175</doi>
+      <video href="2022.emnlp-main.175.mp4"/>
     </paper>
     <paper id="176">
       <title>Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning</title>
@@ -2403,6 +2577,7 @@
       <url hash="48a4ca6f">2022.emnlp-main.183</url>
       <bibkey>madaan-etal-2022-memory</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.183</doi>
+      <video href="2022.emnlp-main.183.mp4"/>
     </paper>
     <paper id="184">
       <title><fixed-case>LVP</fixed-case>-<fixed-case>M</fixed-case>3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation</title>
@@ -2511,6 +2686,7 @@
       <url hash="d6ff2591">2022.emnlp-main.191</url>
       <bibkey>xi-etal-2022-musied</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.191</doi>
+      <video href="2022.emnlp-main.191.mp4"/>
     </paper>
     <paper id="192">
       <title>Reproducibility Issues for <fixed-case>BERT</fixed-case>-based Evaluation Metrics</title>
@@ -2685,6 +2861,7 @@
       <url hash="80c89da3">2022.emnlp-main.204</url>
       <bibkey>wang-etal-2022-r2f</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.204</doi>
+      <video href="2022.emnlp-main.204.mp4"/>
     </paper>
     <paper id="205">
       <title>Revisiting Pre-trained Language Models and their Evaluation for <fixed-case>A</fixed-case>rabic Natural Language Processing</title>
@@ -2737,6 +2914,7 @@
       <url hash="51ba38ef">2022.emnlp-main.207</url>
       <bibkey>wang-etal-2022-knowledge</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.207</doi>
+      <video href="2022.emnlp-main.207.mp4"/>
     </paper>
     <paper id="208">
       <title>On the Evaluation Metrics for Paraphrase Generation</title>
@@ -2789,6 +2967,7 @@
       <url hash="ee872981">2022.emnlp-main.211</url>
       <bibkey>qi-etal-2022-rasat</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.211</doi>
+      <video href="2022.emnlp-main.211.mp4"/>
     </paper>
     <paper id="212">
       <title><fixed-case>COM</fixed-case>-<fixed-case>MRC</fixed-case>: A <fixed-case>CO</fixed-case>ntext-Masked Machine Reading Comprehension Framework for Aspect Sentiment Triplet Extraction</title>
@@ -2892,6 +3071,7 @@
       <url hash="0fc224c5">2022.emnlp-main.219</url>
       <bibkey>yang-etal-2022-face</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.219</doi>
+      <video href="2022.emnlp-main.219.mp4"/>
     </paper>
     <paper id="220">
       <title><fixed-case>F</fixed-case>ine<fixed-case>D</fixed-case>-Eval: Fine-grained Automatic Dialogue-Level Evaluation</title>
@@ -2934,6 +3114,7 @@
       <attachment type="software" hash="3b7fbd04">2022.emnlp-main.222.software.zip</attachment>
       <bibkey>deng-etal-2022-rlprompt</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.222</doi>
+      <video href="2022.emnlp-main.222.mp4"/>
     </paper>
     <paper id="223">
       <title><fixed-case>D</fixed-case>is<fixed-case>C</fixed-case>up: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation</title>
@@ -2963,6 +3144,7 @@
       <attachment type="software" hash="4688d02a">2022.emnlp-main.224.software.zip</attachment>
       <bibkey>he-etal-2022-cpl</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.224</doi>
+      <video href="2022.emnlp-main.224.mp4"/>
     </paper>
     <paper id="225">
       <title>Red Teaming Language Models with Language Models</title>
@@ -3009,6 +3191,7 @@
       <url hash="973ac54a">2022.emnlp-main.227</url>
       <bibkey>wang-etal-2022-spanproto</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.227</doi>
+      <video href="2022.emnlp-main.227.mp4"/>
     </paper>
     <paper id="228">
       <title>Discovering Differences in the Representation of People using Contextualized Semantic Axes</title>
@@ -3020,6 +3203,7 @@
       <url hash="b3562e60">2022.emnlp-main.228</url>
       <bibkey>lucy-etal-2022-discovering</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.228</doi>
+      <video href="2022.emnlp-main.228.mp4"/>
     </paper>
     <paper id="229">
       <title>Generating Literal and Implied Subquestions to Fact-check Complex Claims</title>
@@ -3032,6 +3216,7 @@
       <url hash="1c09cbfd">2022.emnlp-main.229</url>
       <bibkey>chen-etal-2022-generating</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.229</doi>
+      <video href="2022.emnlp-main.229.mp4"/>
     </paper>
     <paper id="230">
       <title>Machine Translation Robustness to Natural Asemantic Variation</title>
@@ -3066,6 +3251,7 @@
       <url hash="8c2326c1">2022.emnlp-main.232</url>
       <bibkey>sultan-shahaf-2022-life</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.232</doi>
+      <video href="2022.emnlp-main.232.mp4"/>
     </paper>
     <paper id="233">
       <title>Language Contamination Helps Explains the Cross-lingual Capabilities of <fixed-case>E</fixed-case>nglish Pretrained Models</title>
@@ -3112,6 +3298,7 @@
       <url hash="dbb2c44d">2022.emnlp-main.236</url>
       <bibkey>zheng-etal-2022-distilling</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.236</doi>
+      <video href="2022.emnlp-main.236.mp4"/>
     </paper>
     <paper id="237">
       <title>Exploring the Secrets Behind the Learning Difficulty of Meaning Representations for Semantic Parsing</title>
@@ -3137,6 +3324,7 @@
       <url hash="96ea0ff4">2022.emnlp-main.238</url>
       <bibkey>mcinerney-etal-2022-thats</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.238</doi>
+      <video href="2022.emnlp-main.238.mp4"/>
     </paper>
     <paper id="239">
       <title>Unsupervised Tokenization Learning</title>
@@ -3147,6 +3335,7 @@
       <url hash="d85ef451">2022.emnlp-main.239</url>
       <bibkey>kolonin-ramesh-2022-unsupervised</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.239</doi>
+      <video href="2022.emnlp-main.239.mp4"/>
     </paper>
     <paper id="240">
       <title>A Template-based Method for Constrained Neural Machine Translation</title>
@@ -3303,6 +3492,7 @@
       <url hash="75ab9cf3">2022.emnlp-main.251</url>
       <bibkey>stacey-etal-2022-logical</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.251</doi>
+      <video href="2022.emnlp-main.251.mp4"/>
     </paper>
     <paper id="252">
       <title>How to disagree well: Investigating the dispute tactics used on <fixed-case>W</fixed-case>ikipedia</title>
@@ -3421,6 +3611,7 @@
       <url hash="623edbd1">2022.emnlp-main.261</url>
       <bibkey>white-etal-2022-mixed</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.261</doi>
+      <video href="2022.emnlp-main.261.mp4"/>
     </paper>
     <paper id="262">
       <title>On Measuring the Intrinsic Few-Shot Hardness of Datasets</title>
@@ -3599,6 +3790,7 @@
       <url hash="582dc63f">2022.emnlp-main.274</url>
       <bibkey>dai-etal-2022-cgodial</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.274</doi>
+      <video href="2022.emnlp-main.274.mp4"/>
     </paper>
     <paper id="275">
       <title>Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding</title>
@@ -3638,6 +3830,7 @@
       <url hash="7113f53f">2022.emnlp-main.277</url>
       <bibkey>shridhar-etal-2022-automatic</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.277</doi>
+      <video href="2022.emnlp-main.277.mp4"/>
     </paper>
     <paper id="278">
       <title>Mixture of Attention Heads: Selecting Attention Heads Per Token</title>
@@ -3681,6 +3874,7 @@
       <url hash="b784d47e">2022.emnlp-main.280</url>
       <bibkey>yoon-etal-2022-information</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.280</doi>
+      <video href="2022.emnlp-main.280.mp4"/>
     </paper>
     <paper id="281">
       <title><fixed-case>DSM</fixed-case>: Question Generation over Knowledge Base via Modeling Diverse Subgraphs with Meta-learner</title>
@@ -3695,6 +3889,7 @@
       <url hash="151d5007">2022.emnlp-main.281</url>
       <bibkey>guo-etal-2022-dsm</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.281</doi>
+      <video href="2022.emnlp-main.281.mp4"/>
     </paper>
     <paper id="282">
       <title><fixed-case>R</fixed-case>el<fixed-case>U</fixed-case>-Net: Syntax-aware Graph <fixed-case>U</fixed-case>-Net for Relational Triple Extraction</title>
@@ -3718,6 +3913,7 @@
       <url hash="492379af">2022.emnlp-main.283</url>
       <bibkey>bassignana-etal-2022-evidence</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.283</doi>
+      <video href="2022.emnlp-main.283.mp4"/>
     </paper>
     <paper id="284">
       <title>Chunk-based Nearest Neighbor Machine Translation</title>
@@ -3757,6 +3953,7 @@
       <attachment type="software" hash="ef1fb897">2022.emnlp-main.286.software.zip</attachment>
       <bibkey>pan-etal-2022-inductive</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.286</doi>
+      <video href="2022.emnlp-main.286.mp4"/>
     </paper>
     <paper id="287">
       <title>Improving <fixed-case>C</fixed-case>hinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity</title>
@@ -3852,6 +4049,7 @@
       <url hash="b031f967">2022.emnlp-main.293</url>
       <bibkey>friedman-etal-2022-finding</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.293</doi>
+      <video href="2022.emnlp-main.293.mp4"/>
     </paper>
     <paper id="294">
       <title>Retrieval Augmentation for Commonsense Reasoning: A Unified Approach</title>
@@ -3896,6 +4094,7 @@
       <url hash="28b6f81f">2022.emnlp-main.296</url>
       <bibkey>yang-etal-2022-re3</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.296</doi>
+      <video href="2022.emnlp-main.296.mp4"/>
     </paper>
     <paper id="297">
       <title>Does Joint Training Really Help Cascaded Speech Translation?</title>
@@ -3909,6 +4108,7 @@
       <url hash="a8073e32">2022.emnlp-main.297</url>
       <bibkey>tran-etal-2022-joint</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.297</doi>
+      <video href="2022.emnlp-main.297.mp4"/>
     </paper>
     <paper id="298">
       <title><fixed-case>M</fixed-case>asakha<fixed-case>NER</fixed-case> 2.0: <fixed-case>A</fixed-case>frica-centric Transfer Learning for Named Entity Recognition</title>
@@ -3962,6 +4162,7 @@
       <url hash="136ec5a9">2022.emnlp-main.299</url>
       <bibkey>benotti-blackburn-2022-ethics</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.299</doi>
+      <video href="2022.emnlp-main.299.mp4"/>
     </paper>
     <paper id="300">
       <title>Continued Pretraining for Better Zero- and Few-Shot Promptability</title>
@@ -3977,6 +4178,7 @@
       <url hash="f62147f5">2022.emnlp-main.300</url>
       <bibkey>wu-etal-2022-continued</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.300</doi>
+      <video href="2022.emnlp-main.300.mp4"/>
     </paper>
     <paper id="301">
       <title>Less is More: Summary of Long Instructions is Better for Program Synthesis</title>
@@ -3989,6 +4191,7 @@
       <url hash="5beccb7b">2022.emnlp-main.301</url>
       <bibkey>kuznia-etal-2022-less</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.301</doi>
+      <video href="2022.emnlp-main.301.mp4"/>
     </paper>
     <paper id="302">
       <title>Is a Question Decomposition Unit All We Need?</title>
@@ -4108,6 +4311,7 @@
       <bibkey>huang-etal-2022-metalogic</bibkey>
       <attachment type="software" hash="9b190d05">2022.emnlp-main.310.software.zip</attachment>
       <doi>10.18653/v1/2022.emnlp-main.310</doi>
+      <video href="2022.emnlp-main.310.mp4"/>
     </paper>
     <paper id="311">
       <title>Explicit Query Rewriting for Conversational Dense Retrieval</title>
@@ -4216,6 +4420,7 @@
       <url hash="aade2944">2022.emnlp-main.318</url>
       <bibkey>zheng-etal-2022-candidate</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.318</doi>
+      <video href="2022.emnlp-main.318.mp4"/>
     </paper>
     <paper id="319">
       <title>Evaluating Parameter Efficient Learning for Generation</title>
@@ -4268,6 +4473,7 @@
       <url hash="499ba9f3">2022.emnlp-main.322</url>
       <bibkey>yang-ma-2022-improving</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.322</doi>
+      <video href="2022.emnlp-main.322.mp4"/>
     </paper>
     <paper id="323">
       <title>Differentially Private Language Models for Secure Data Sharing</title>
@@ -4454,6 +4660,7 @@
       <url hash="15045782">2022.emnlp-main.335</url>
       <bibkey>peng-etal-2022-copen</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.335</doi>
+      <video href="2022.emnlp-main.335.mp4"/>
     </paper>
     <paper id="336">
       <title>Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network</title>
@@ -4557,6 +4764,7 @@
       <url hash="ce745d40">2022.emnlp-main.341</url>
       <bibkey>liu-etal-2022-metafill</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.341</doi>
+      <video href="2022.emnlp-main.341.mp4"/>
     </paper>
     <paper id="342">
       <title><fixed-case>DRLK</fixed-case>: Dynamic Hierarchical Reasoning with Language Model and Knowledge Graph for Question Answering</title>
@@ -4569,6 +4777,7 @@
       <url hash="5dd40d51">2022.emnlp-main.342</url>
       <bibkey>zhang-etal-2022-drlk</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.342</doi>
+      <video href="2022.emnlp-main.342.mp4"/>
     </paper>
     <paper id="343">
       <title><fixed-case>AEG</fixed-case>: Argumentative Essay Generation via A Dual-Decoder Model with Content Planning</title>
@@ -4613,6 +4822,7 @@
       <url hash="30addbb9">2022.emnlp-main.345</url>
       <bibkey>ma-etal-2022-wider</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.345</doi>
+      <video href="2022.emnlp-main.345.mp4"/>
     </paper>
     <paper id="346">
       <title>An Efficient Memory-Augmented Transformer for Knowledge-Intensive <fixed-case>NLP</fixed-case> Tasks</title>
@@ -4653,6 +4863,7 @@
       <url hash="c706fccc">2022.emnlp-main.348</url>
       <bibkey>mikhailov-etal-2022-rucola</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.348</doi>
+      <video href="2022.emnlp-main.348.mp4"/>
     </paper>
     <paper id="349">
       <title>Complex Hyperbolic Knowledge Graph Embeddings with Fast <fixed-case>F</fixed-case>ourier Transform</title>
@@ -4815,6 +5026,7 @@
       <url hash="24eed987">2022.emnlp-main.360</url>
       <bibkey>kumar-etal-2022-indicnlg</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.360</doi>
+      <video href="2022.emnlp-main.360.mp4"/>
     </paper>
     <paper id="361">
       <title>Improving Machine Translation with Phrase Pair Injection and Corpus Filtering</title>
@@ -4825,6 +5037,7 @@
       <url hash="fc62714b">2022.emnlp-main.361</url>
       <bibkey>batheja-bhattacharyya-2022-improving</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.361</doi>
+      <video href="2022.emnlp-main.361.mp4"/>
     </paper>
     <paper id="362">
       <title>An Anchor-based Relative Position Embedding Method for Cross-Modal Tasks</title>
@@ -4867,6 +5080,7 @@
       <url hash="ec5b944c">2022.emnlp-main.364</url>
       <bibkey>ju-etal-2022-telemelody</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.364</doi>
+      <video href="2022.emnlp-main.364.mp4"/>
     </paper>
     <paper id="365">
       <title><fixed-case>SEEN</fixed-case>: Structured Event Enhancement Network for Explainable Need Detection of Information Recall Assistance</title>
@@ -4879,6 +5093,7 @@
       <url hash="ebc6c48b">2022.emnlp-main.365</url>
       <bibkey>lin-etal-2022-seen</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.365</doi>
+      <video href="2022.emnlp-main.365.mp4"/>
     </paper>
     <paper id="366">
       <title>Rethinking Style Transformer with Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained Model</title>
@@ -4960,6 +5175,7 @@
       <url hash="675f2f40">2022.emnlp-main.371</url>
       <bibkey>wang-etal-2022-helping</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.371</doi>
+      <video href="2022.emnlp-main.371.mp4"/>
     </paper>
     <paper id="372">
       <title><fixed-case>RACE</fixed-case>: Retrieval-augmented Commit Message Generation</title>
@@ -5013,6 +5229,7 @@
       <url hash="29221926">2022.emnlp-main.375</url>
       <bibkey>chen-etal-2022-murag</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.375</doi>
+      <video href="2022.emnlp-main.375.mp4"/>
     </paper>
     <paper id="376">
       <title><fixed-case>PHEE</fixed-case>: A Dataset for Pharmacovigilance Event Extraction from Text</title>
@@ -5050,6 +5267,7 @@
       <url hash="88ba1ee2">2022.emnlp-main.378</url>
       <bibkey>han-etal-2022-simqa</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.378</doi>
+      <video href="2022.emnlp-main.378.mp4"/>
     </paper>
     <paper id="379">
       <title>Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations</title>
@@ -5097,6 +5315,7 @@
       <url hash="e3073b5e">2022.emnlp-main.382</url>
       <bibkey>zhong-etal-2022-training</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.382</doi>
+      <video href="2022.emnlp-main.382.mp4"/>
     </paper>
     <paper id="383">
       <title>Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages</title>
@@ -5136,6 +5355,7 @@
       <url hash="20ae6a39">2022.emnlp-main.385</url>
       <bibkey>slobodkin-etal-2022-controlled</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.385</doi>
+      <video href="2022.emnlp-main.385.mp4"/>
     </paper>
     <paper id="386">
       <title>Questioning the Validity of Summarization Datasets and Improving Their Factual Consistency</title>
@@ -5192,6 +5412,7 @@
       <url hash="d3ec374c">2022.emnlp-main.389</url>
       <bibkey>wolhandler-etal-2022-multi</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.389</doi>
+      <video href="2022.emnlp-main.389.mp4"/>
     </paper>
     <paper id="390">
       <title><fixed-case>B</fixed-case>io<fixed-case>R</fixed-case>eader: a Retrieval-Enhanced Text-to-Text Transformer for Biomedical Literature</title>
@@ -5204,6 +5425,7 @@
       <url hash="69afb1e3">2022.emnlp-main.390</url>
       <bibkey>frisoni-etal-2022-bioreader</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.390</doi>
+      <video href="2022.emnlp-main.390.mp4"/>
     </paper>
     <paper id="391">
       <title><fixed-case>T</fixed-case>-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation</title>
@@ -5245,6 +5467,7 @@
       <url hash="66cfae4a">2022.emnlp-main.393</url>
       <bibkey>hossain-blanco-2022-leveraging</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.393</doi>
+      <video href="2022.emnlp-main.393.mp4"/>
     </paper>
     <paper id="394">
       <title><fixed-case>G</fixed-case>raph<fixed-case>Q</fixed-case> <fixed-case>IR</fixed-case>: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation</title>
@@ -5296,6 +5519,7 @@
       <url hash="034656b7">2022.emnlp-main.397</url>
       <bibkey>glockner-etal-2022-missing</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.397</doi>
+      <video href="2022.emnlp-main.397.mp4"/>
     </paper>
     <paper id="398">
       <title>A Framework for Adapting Pre-Trained Language Models to Knowledge Graph Completion</title>
@@ -5382,6 +5606,7 @@
       <url hash="d7cb1dd3">2022.emnlp-main.404</url>
       <bibkey>marchisio-etal-2022-isovec</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.404</doi>
+      <video href="2022.emnlp-main.404.mp4"/>
     </paper>
     <paper id="405">
       <title>Adversarial Concept Erasure in Kernel Space</title>
@@ -5470,6 +5695,7 @@
       <url hash="9920c6e5">2022.emnlp-main.411</url>
       <bibkey>aly-vlachos-2022-natural</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.411</doi>
+      <video href="2022.emnlp-main.411.mp4"/>
     </paper>
     <paper id="412">
       <title><fixed-case>AX</fixed-case>-<fixed-case>MABSA</fixed-case>: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis</title>
@@ -5492,6 +5718,7 @@
       <url hash="5e95e09a">2022.emnlp-main.413</url>
       <bibkey>mirzaee-kordjamshidi-2022-transfer</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.413</doi>
+      <video href="2022.emnlp-main.413.mp4"/>
     </paper>
     <paper id="414">
       <title>A Survey of Active Learning for Natural Language Processing</title>
@@ -5651,6 +5878,7 @@
       <url hash="3eb2c270">2022.emnlp-main.425</url>
       <bibkey>shi-etal-2022-just</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.425</doi>
+      <video href="2022.emnlp-main.425.mp4"/>
     </paper>
     <paper id="426">
       <title>Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents</title>
@@ -5701,6 +5929,7 @@
       <url hash="382ed786">2022.emnlp-main.429</url>
       <bibkey>feng-etal-2022-uln</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.429</doi>
+      <video href="2022.emnlp-main.429.mp4"/>
     </paper>
     <paper id="430">
       <title>Federated Model Decomposition with Private Vocabulary for Text Classification</title>
@@ -5768,6 +5997,7 @@
       <url hash="3b7936cf">2022.emnlp-main.434</url>
       <bibkey>wang-etal-2022-breaking</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.434</doi>
+      <video href="2022.emnlp-main.434.mp4"/>
     </paper>
     <paper id="435">
       <title>Boundary-Driven Table-Filling for Aspect Sentiment Triplet Extraction</title>
@@ -5822,6 +6052,7 @@
       <url hash="045a48fa">2022.emnlp-main.437</url>
       <bibkey>deng-etal-2022-title2event</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.437</doi>
+      <video href="2022.emnlp-main.437.mp4"/>
     </paper>
     <paper id="438">
       <title>Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models</title>
@@ -5833,6 +6064,7 @@
       <url hash="4e712256">2022.emnlp-main.438</url>
       <bibkey>malaviya-etal-2022-cascading</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.438</doi>
+      <video href="2022.emnlp-main.438.mp4"/>
     </paper>
     <paper id="439">
       <title>Teaching Broad Reasoning Skills for Multi-Step <fixed-case>QA</fixed-case> by Generating Hard Contexts</title>
@@ -5845,6 +6077,7 @@
       <url hash="1ab6b6b3">2022.emnlp-main.439</url>
       <bibkey>trivedi-etal-2022-teaching</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.439</doi>
+      <video href="2022.emnlp-main.439.mp4"/>
     </paper>
     <paper id="440">
       <title><fixed-case>ADDMU</fixed-case>: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation</title>
@@ -5857,6 +6090,7 @@
       <url hash="cf78826f">2022.emnlp-main.440</url>
       <bibkey>yin-etal-2022-addmu</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.440</doi>
+      <video href="2022.emnlp-main.440.mp4"/>
     </paper>
     <paper id="441">
       <title><fixed-case>G</fixed-case>-<fixed-case>MAP</fixed-case>: General Memory-Augmented Pre-trained Language Model for Domain Tasks</title>
@@ -5922,6 +6156,7 @@
       <url hash="7555a53e">2022.emnlp-main.445</url>
       <bibkey>sun-etal-2022-reduce</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.445</doi>
+      <video href="2022.emnlp-main.445.mp4"/>
     </paper>
     <paper id="446">
       <title><fixed-case>ATTEMPT</fixed-case>: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts</title>
@@ -5971,6 +6206,7 @@
       <url hash="2fccfcb7">2022.emnlp-main.449</url>
       <bibkey>sun-etal-2022-meta</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.449</doi>
+      <video href="2022.emnlp-main.449.mp4"/>
     </paper>
     <paper id="450">
       <title>Understanding and Improving Knowledge Distillation for Quantization Aware Training of Large Transformer Encoders</title>
@@ -5985,6 +6221,7 @@
       <attachment type="software" hash="86b3b92d">2022.emnlp-main.450.software.zip</attachment>
       <bibkey>kim-etal-2022-understanding</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.450</doi>
+      <video href="2022.emnlp-main.450.mp4"/>
     </paper>
     <paper id="451">
       <title>Exploring Mode Connectivity for Pre-trained Language Models</title>
@@ -6037,6 +6274,7 @@
       <url hash="9906cc97">2022.emnlp-main.454</url>
       <bibkey>xu-etal-2022-improving</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.454</doi>
+      <video href="2022.emnlp-main.454.mp4"/>
     </paper>
     <paper id="455">
       <title>Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding</title>
@@ -6084,6 +6322,7 @@
       <url hash="a0ce0753">2022.emnlp-main.458</url>
       <bibkey>huang-etal-2022-unifying</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.458</doi>
+      <video href="2022.emnlp-main.458.mp4"/>
     </paper>
     <paper id="459">
       <title>Modeling Label Correlations for Ultra-Fine Entity Typing with Neural Pairwise Conditional Random Field</title>
@@ -6108,6 +6347,7 @@
       <url hash="79a67408">2022.emnlp-main.460</url>
       <bibkey>chakrabarty-etal-2022-help</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.460</doi>
+      <video href="2022.emnlp-main.460.mp4"/>
     </paper>
     <paper id="461">
       <title>Open Relation and Event Type Discovery with Type Abstraction</title>
@@ -6147,6 +6387,7 @@
       <attachment type="software" hash="9a486ebe">2022.emnlp-main.463.software.zip</attachment>
       <bibkey>gong-etal-2022-revisiting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.463</doi>
+      <video href="2022.emnlp-main.463.mp4"/>
     </paper>
     <paper id="464">
       <title><fixed-case>R</fixed-case>2<fixed-case>D</fixed-case>2: Robust Data-to-Text with Replacement Detection</title>
@@ -6173,6 +6414,7 @@
       <attachment type="dataset" hash="f3855dc3">2022.emnlp-main.465.dataset.zip</attachment>
       <bibkey>putri-oh-2022-idk</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.465</doi>
+      <video href="2022.emnlp-main.465.mp4"/>
     </paper>
     <paper id="466">
       <title><fixed-case>XLM</fixed-case>-<fixed-case>D</fixed-case>: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine Translation</title>
@@ -6264,6 +6506,7 @@
       <url hash="b116228b">2022.emnlp-main.472</url>
       <bibkey>kim-etal-2022-break</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.472</doi>
+      <video href="2022.emnlp-main.472.mp4"/>
     </paper>
     <paper id="473">
       <title>The Devil in Linear Transformer</title>
@@ -6279,6 +6522,7 @@
       <url hash="a4e54b57">2022.emnlp-main.473</url>
       <bibkey>qin-etal-2022-devil</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.473</doi>
+      <video href="2022.emnlp-main.473.mp4"/>
     </paper>
     <paper id="474">
       <title>Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective</title>
@@ -6448,6 +6692,7 @@
       <url hash="80944c81">2022.emnlp-main.485</url>
       <bibkey>kongyoung-etal-2022-monoqa</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.485</doi>
+      <video href="2022.emnlp-main.485.mp4"/>
     </paper>
     <paper id="486">
       <title>Composing Ci with Reinforced Non-autoregressive Text Generation</title>
@@ -6538,6 +6783,7 @@
       <url hash="1e562c1b">2022.emnlp-main.491</url>
       <bibkey>xie-etal-2022-wr</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.491</doi>
+      <video href="2022.emnlp-main.491.mp4"/>
     </paper>
     <paper id="492">
       <title>Eeny, meeny, miny, moe. How to choose data for morphological inflection.</title>
@@ -6602,6 +6848,7 @@
       <attachment type="software" hash="64799564">2022.emnlp-main.496.software.zip</attachment>
       <bibkey>senge-etal-2022-one</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.496</doi>
+      <video href="2022.emnlp-main.496.mp4"/>
     </paper>
     <paper id="497">
       <title>Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario</title>
@@ -6629,6 +6876,7 @@
       <url hash="12c547f8">2022.emnlp-main.498</url>
       <bibkey>kim-etal-2022-tutoring</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.498</doi>
+      <video href="2022.emnlp-main.498.mp4"/>
     </paper>
     <paper id="499">
       <title>Does Corpus Quality Really Matter for Low-Resource Languages?</title>
@@ -6654,6 +6902,7 @@
       <url hash="b9373047">2022.emnlp-main.500</url>
       <bibkey>plepi-etal-2022-unifying</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.500</doi>
+      <video href="2022.emnlp-main.500.mp4"/>
     </paper>
     <paper id="501">
       <title>Does Self-Rationalization Improve Robustness to Spurious Correlations?</title>
@@ -6665,6 +6914,7 @@
       <url hash="9a4e7a00">2022.emnlp-main.501</url>
       <bibkey>ross-etal-2022-self</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.501</doi>
+      <video href="2022.emnlp-main.501.mp4"/>
     </paper>
     <paper id="502">
       <title>Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking</title>
@@ -6678,6 +6928,7 @@
       <url hash="d988c9fd">2022.emnlp-main.502</url>
       <bibkey>lee-etal-2022-efficient-pre</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.502</doi>
+      <video href="2022.emnlp-main.502.mp4"/>
     </paper>
     <paper id="503">
       <title>Subword Evenness (<fixed-case>S</fixed-case>u<fixed-case>E</fixed-case>) as a Predictor of Cross-lingual Transfer to Low-resource Languages</title>
@@ -6819,6 +7070,7 @@
       <url hash="94cc8c7a">2022.emnlp-main.513</url>
       <bibkey>foroutan-etal-2022-discovering</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.513</doi>
+      <video href="2022.emnlp-main.513.mp4"/>
     </paper>
     <paper id="514">
       <title>Parameter-Efficient Tuning Makes a Good Classification Head</title>
@@ -6895,6 +7147,7 @@
       <url hash="d72cc3ec">2022.emnlp-main.519</url>
       <bibkey>aumiller-etal-2022-eur</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.519</doi>
+      <video href="2022.emnlp-main.519.mp4"/>
     </paper>
     <paper id="520">
       <title>Differentiable Data Augmentation for Contrastive Sentence Representation Learning</title>
@@ -7002,6 +7255,7 @@
       <url hash="53d62d9a">2022.emnlp-main.527</url>
       <bibkey>muller-eberstein-etal-2022-spectral</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.527</doi>
+      <video href="2022.emnlp-main.527.mp4"/>
     </paper>
     <paper id="528">
       <title><fixed-case>QAS</fixed-case>em Parsing: Text-to-text Modeling of <fixed-case>QA</fixed-case>-based Semantics</title>
@@ -7016,6 +7270,7 @@
       <url hash="6e471aa0">2022.emnlp-main.528</url>
       <bibkey>klein-etal-2022-qasem</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.528</doi>
+      <video href="2022.emnlp-main.528.mp4"/>
     </paper>
     <paper id="529">
       <title>Keyphrase Generation via Soft and Hard Semantic Corrections</title>
@@ -7028,6 +7283,7 @@
       <url hash="1c1e505b">2022.emnlp-main.529</url>
       <bibkey>zhao-etal-2022-keyphrase</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.529</doi>
+      <video href="2022.emnlp-main.529.mp4"/>
     </paper>
     <paper id="530">
       <title>Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval</title>
@@ -7041,6 +7297,7 @@
       <url hash="69519796">2022.emnlp-main.530</url>
       <bibkey>jung-etal-2022-modal</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.530</doi>
+      <video href="2022.emnlp-main.530.mp4"/>
     </paper>
     <paper id="531">
       <title><fixed-case>D</fixed-case>u<fixed-case>QM</fixed-case>: A <fixed-case>C</fixed-case>hinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models</title>
@@ -7070,6 +7327,7 @@
       <url hash="821371e8">2022.emnlp-main.532</url>
       <bibkey>sarti-etal-2022-divemt</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.532</doi>
+      <video href="2022.emnlp-main.532.mp4"/>
     </paper>
     <paper id="533">
       <title>Bridging Fairness and Environmental Sustainability in Natural Language Processing</title>
@@ -7118,6 +7376,7 @@
       <url hash="e8acba6d">2022.emnlp-main.536</url>
       <bibkey>xue-aletras-2022-hashformers</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.536</doi>
+      <video href="2022.emnlp-main.536.mp4"/>
     </paper>
     <paper id="537">
       <title><fixed-case>M</fixed-case>atch<fixed-case>P</fixed-case>rompt: Prompt-based Open Relation Extraction with Semantic Consistency Guided Clustering</title>
@@ -7193,6 +7452,7 @@
       <url hash="78d61392">2022.emnlp-main.542</url>
       <bibkey>xu-etal-2022-towards-robust</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.542</doi>
+      <video href="2022.emnlp-main.542.mp4"/>
     </paper>
     <paper id="543">
       <title>Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence</title>
@@ -7218,6 +7478,7 @@
       <url hash="ff23056d">2022.emnlp-main.544</url>
       <bibkey>giulianelli-2022-towards</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.544</doi>
+      <video href="2022.emnlp-main.544.mp4"/>
     </paper>
     <paper id="545">
       <title><fixed-case>L</fixed-case>ite<fixed-case>VL</fixed-case>: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling</title>
@@ -7303,6 +7564,7 @@
       <url hash="104aeb6c">2022.emnlp-main.551</url>
       <bibkey>wu-mooney-2022-entity</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.551</doi>
+      <video href="2022.emnlp-main.551.mp4"/>
     </paper>
     <paper id="552">
       <title>Cross-Linguistic Syntactic Difference in Multilingual <fixed-case>BERT</fixed-case>: How Good is It and How Does It Affect Transfer?</title>
@@ -7318,6 +7580,7 @@
       <url hash="7a299dd8">2022.emnlp-main.552</url>
       <bibkey>xu-etal-2022-cross</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.552</doi>
+      <video href="2022.emnlp-main.552.mp4"/>
     </paper>
     <paper id="553">
       <title>“It’s Not Just Hate”: A Multi-Dimensional Perspective on Detecting Harmful Speech Online</title>
@@ -7332,6 +7595,7 @@
       <url hash="6f5aef9a">2022.emnlp-main.553</url>
       <bibkey>bianchi-etal-2022-just</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.553</doi>
+      <video href="2022.emnlp-main.553.mp4"/>
     </paper>
     <paper id="554">
       <title>Long Text Generation with Topic-aware Discrete Latent Variable Model</title>
@@ -7361,6 +7625,7 @@
       <url hash="e36b12e0">2022.emnlp-main.555</url>
       <bibkey>shu-etal-2022-tiara</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.555</doi>
+      <video href="2022.emnlp-main.555.mp4"/>
     </paper>
     <paper id="556">
       <title>Structure-Unified <fixed-case>M</fixed-case>-Tree Coding Solver for Math Word Problem</title>
@@ -7391,6 +7656,7 @@
       <url hash="d0fdb402">2022.emnlp-main.557</url>
       <bibkey>shao-etal-2022-formlm</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.557</doi>
+      <video href="2022.emnlp-main.557.mp4"/>
     </paper>
     <paper id="558">
       <title>Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework</title>
@@ -7461,6 +7727,7 @@
       <url hash="8658af6d">2022.emnlp-main.562</url>
       <bibkey>chen-etal-2022-towards-table</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.562</doi>
+      <video href="2022.emnlp-main.562.mp4"/>
     </paper>
     <paper id="563">
       <title>Hierarchical Phrase-Based Sequence-to-Sequence Learning</title>
@@ -7485,6 +7752,7 @@
       <url hash="db43184b">2022.emnlp-main.564</url>
       <bibkey>sprague-etal-2022-natural</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.564</doi>
+      <video href="2022.emnlp-main.564.mp4"/>
     </paper>
     <paper id="565">
       <title>Character-centric Story Visualization via Visual Planning and Token Alignment</title>
@@ -7582,6 +7850,7 @@
       <url hash="0b5f490b">2022.emnlp-main.571</url>
       <bibkey>mohammadshahi-etal-2022-small</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.571</doi>
+      <video href="2022.emnlp-main.571.mp4"/>
     </paper>
     <paper id="572">
       <title><fixed-case>T</fixed-case>ext<fixed-case>F</fixed-case>usion: Privacy-Preserving Pre-trained Model Inference via Token Fusion</title>
@@ -7611,6 +7880,7 @@
       <url hash="6685149c">2022.emnlp-main.573</url>
       <bibkey>feng-boyd-graber-2022-learning</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.573</doi>
+      <video href="2022.emnlp-main.573.mp4"/>
     </paper>
     <paper id="574">
       <title><fixed-case>C</fixed-case>onsist<fixed-case>TL</fixed-case>: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation</title>
@@ -7624,6 +7894,7 @@
       <url hash="453ae14b">2022.emnlp-main.574</url>
       <bibkey>li-etal-2022-consisttl</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.574</doi>
+      <video href="2022.emnlp-main.574.mp4"/>
     </paper>
     <paper id="575">
       <title>Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection</title>
@@ -7648,6 +7919,7 @@
       <url hash="f98b6d7f">2022.emnlp-main.576</url>
       <bibkey>wang-etal-2022-ielm</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.576</doi>
+      <video href="2022.emnlp-main.576.mp4"/>
     </paper>
     <paper id="577">
       <title><fixed-case>C</fixed-case>on<fixed-case>NER</fixed-case>: Consistency Training for Cross-lingual Named Entity Recognition</title>
@@ -7701,6 +7973,7 @@
       <url hash="f28c485a">2022.emnlp-main.580</url>
       <bibkey>tan-etal-2022-revisiting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.580</doi>
+      <video href="2022.emnlp-main.580.mp4"/>
     </paper>
     <paper id="581">
       <title>Towards Summary Candidates Fusion</title>
@@ -7722,6 +7995,7 @@
       <url hash="b68179d4">2022.emnlp-main.582</url>
       <bibkey>zhao-calapodescu-2022-multimodal</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.582</doi>
+      <video href="2022.emnlp-main.582.mp4"/>
     </paper>
     <paper id="583">
       <title><fixed-case>T</fixed-case>ran<fixed-case>SHER</fixed-case>: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction</title>
@@ -7784,6 +8058,7 @@
       <attachment type="dataset" hash="b983cc9a">2022.emnlp-main.587.dataset.zip</attachment>
       <bibkey>fei-etal-2022-beyond</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.587</doi>
+      <video href="2022.emnlp-main.587.mp4"/>
     </paper>
     <paper id="588">
       <title>Generalizing over Long Tail Concepts for Medical Term Normalization</title>
@@ -7811,6 +8086,7 @@
       <url hash="62a2109c">2022.emnlp-main.589</url>
       <bibkey>song-etal-2022-unsupervised</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.589</doi>
+      <video href="2022.emnlp-main.589.mp4"/>
     </paper>
     <paper id="590">
       <title>Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks</title>
@@ -7825,6 +8101,7 @@
       <url hash="f6b4f735">2022.emnlp-main.590</url>
       <bibkey>leong-etal-2022-bloom</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.590</doi>
+      <video href="2022.emnlp-main.590.mp4"/>
     </paper>
     <paper id="591">
       <title>Disentangling Uncertainty in Machine Translation Evaluation</title>
@@ -7837,6 +8114,7 @@
       <url hash="a4f22107">2022.emnlp-main.591</url>
       <bibkey>zerva-etal-2022-disentangling</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.591</doi>
+      <video href="2022.emnlp-main.591.mp4"/>
     </paper>
     <paper id="592">
       <title>Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing</title>
@@ -7876,6 +8154,7 @@
       <url hash="08da9176">2022.emnlp-main.594</url>
       <bibkey>vallurupalli-etal-2022-poque</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.594</doi>
+      <video href="2022.emnlp-main.594.mp4"/>
     </paper>
     <paper id="595">
       <title>Measuring the Mixing of Contextual Information in the Transformer</title>
@@ -7922,6 +8201,7 @@
       <url hash="bc3e00af">2022.emnlp-main.598</url>
       <bibkey>ravichander-etal-2022-condaqa</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.598</doi>
+      <video href="2022.emnlp-main.598.mp4"/>
     </paper>
     <paper id="599">
       <title>Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer</title>
@@ -7950,6 +8230,7 @@
       <url hash="24a58616">2022.emnlp-main.600</url>
       <bibkey>mohamed-etal-2022-artelingo</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.600</doi>
+      <video href="2022.emnlp-main.600.mp4"/>
     </paper>
     <paper id="601">
       <title>Decoding a Neural Retriever’s Latent Space for Query Suggestion</title>
@@ -8090,6 +8371,7 @@
       <url hash="339fa2bf">2022.emnlp-main.610</url>
       <bibkey>sadat-caragea-2022-hierarchical</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.610</doi>
+      <video href="2022.emnlp-main.610.mp4"/>
     </paper>
     <paper id="611">
       <title>Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering</title>
@@ -8203,6 +8485,7 @@
       <url hash="a2bd5f60">2022.emnlp-main.618</url>
       <bibkey>chong-etal-2022-detecting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.618</doi>
+      <video href="2022.emnlp-main.618.mp4"/>
     </paper>
     <paper id="619">
       <title>Intriguing Properties of Compression on Multilingual Models</title>
@@ -8230,6 +8513,7 @@
       <attachment type="dataset" hash="5eda85c8">2022.emnlp-main.620.dataset.zip</attachment>
       <bibkey>born-etal-2022-sequence</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.620</doi>
+      <video href="2022.emnlp-main.620.mp4"/>
     </paper>
     <paper id="621">
       <title><fixed-case>E</fixed-case>nglish Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings</title>
@@ -8282,6 +8566,7 @@
       <url hash="cb91d4f5">2022.emnlp-main.624</url>
       <bibkey>qiu-etal-2022-evaluating</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.624</doi>
+      <video href="2022.emnlp-main.624.mp4"/>
     </paper>
     <paper id="625">
       <title>“<fixed-case>I</fixed-case>’m sorry to hear that”: Finding New Biases in Language Models with a Holistic Descriptor Dataset</title>
@@ -8309,6 +8594,7 @@
       <url hash="9f439fef">2022.emnlp-main.626</url>
       <bibkey>wang-etal-2022-understanding-multimodal</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.626</doi>
+      <video href="2022.emnlp-main.626.mp4"/>
     </paper>
     <paper id="627">
       <title>Semantic Novelty Detection and Characterization in Factual Text Involving Named Entities</title>
@@ -8372,6 +8658,7 @@
       <attachment type="dataset" hash="491e1bd8">2022.emnlp-main.631.dataset.zip</attachment>
       <bibkey>dou-etal-2022-improving</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.631</doi>
+      <video href="2022.emnlp-main.631.mp4"/>
     </paper>
     <paper id="632">
       <title>Entropy- and Distance-Based Predictors From <fixed-case>GPT</fixed-case>-2 Attention Patterns Predict Reading Times Over and Above <fixed-case>GPT</fixed-case>-2 Surprisal</title>
@@ -8382,6 +8669,7 @@
       <url hash="c91963f9">2022.emnlp-main.632</url>
       <bibkey>oh-schuler-2022-entropy</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.632</doi>
+      <video href="2022.emnlp-main.632.mp4"/>
     </paper>
     <paper id="633">
       <title>A Survey of Computational Framing Analysis Approaches</title>
@@ -8416,6 +8704,7 @@
       <url hash="4a48d13c">2022.emnlp-main.635</url>
       <bibkey>min-etal-2022-dont</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.635</doi>
+      <video href="2022.emnlp-main.635.mp4"/>
     </paper>
     <paper id="636">
       <title><fixed-case>ALFRED</fixed-case>-<fixed-case>L</fixed-case>: Investigating the Role of Language for Action Learning in Interactive Visual Environments</title>
@@ -8432,6 +8721,7 @@
       <bibkey>akula-etal-2022-alfred</bibkey>
       <attachment type="software" hash="7efc1dbc">2022.emnlp-main.636.software.zip</attachment>
       <doi>10.18653/v1/2022.emnlp-main.636</doi>
+      <video href="2022.emnlp-main.636.mp4"/>
     </paper>
     <paper id="637">
       <title>Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence</title>
@@ -8459,6 +8749,7 @@
       <attachment type="software" hash="1760dee4">2022.emnlp-main.638.software.zip</attachment>
       <bibkey>cho-etal-2022-unsupervised</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.638</doi>
+      <video href="2022.emnlp-main.638.mp4"/>
     </paper>
     <paper id="639">
       <title>Weakly-Supervised Temporal Article Grounding</title>
@@ -8491,6 +8782,7 @@
       <url hash="e740cc73">2022.emnlp-main.640</url>
       <bibkey>dong-etal-2022-exploring</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.640</doi>
+      <video href="2022.emnlp-main.640.mp4"/>
     </paper>
     <paper id="641">
       <title>ar<fixed-case>X</fixed-case>iv<fixed-case>E</fixed-case>dits: Understanding the Human Revision Process in Scientific Writing</title>
@@ -8502,6 +8794,7 @@
       <url hash="bdbef8c4">2022.emnlp-main.641</url>
       <bibkey>jiang-etal-2022-arxivedits</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.641</doi>
+      <video href="2022.emnlp-main.641.mp4"/>
     </paper>
     <paper id="642">
       <title>Why Do You Feel This Way? Summarizing Triggers of Emotions in Social Media Posts</title>
@@ -8514,6 +8807,7 @@
       <url hash="a6766ba4">2022.emnlp-main.642</url>
       <bibkey>zhan-etal-2022-feel</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.642</doi>
+      <video href="2022.emnlp-main.642.mp4"/>
     </paper>
     <paper id="643">
       <title>Analogical Math Word Problems Solving with Enhanced Problem-Solution Association</title>
@@ -8536,6 +8830,7 @@
       <url hash="800295dd">2022.emnlp-main.644</url>
       <bibkey>dalvi-mishra-etal-2022-towards</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.644</doi>
+      <video href="2022.emnlp-main.644.mp4"/>
     </paper>
     <paper id="645">
       <title>Knowledge Transfer from Answer Ranking to Answer Generation</title>
@@ -8549,6 +8844,7 @@
       <url hash="c77fbe9e">2022.emnlp-main.645</url>
       <bibkey>gabburo-etal-2022-knowledge</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.645</doi>
+      <video href="2022.emnlp-main.645.mp4"/>
     </paper>
     <paper id="646">
       <title>Perturbation Augmentation for Fairer <fixed-case>NLP</fixed-case></title>
@@ -8563,6 +8859,7 @@
       <url hash="9f1c5b9a">2022.emnlp-main.646</url>
       <bibkey>qian-etal-2022-perturbation</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.646</doi>
+      <video href="2022.emnlp-main.646.mp4"/>
     </paper>
     <paper id="647">
       <title>Automatic Document Selection for Efficient Encoder Pretraining</title>
@@ -8670,6 +8967,7 @@
       <url hash="f0f4df6e">2022.emnlp-main.654</url>
       <bibkey>wan-bansal-2022-evaluating</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.654</doi>
+      <video href="2022.emnlp-main.654.mp4"/>
     </paper>
     <paper id="655">
       <title>Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation</title>
@@ -8683,6 +8981,7 @@
       <url hash="7741c659">2022.emnlp-main.655</url>
       <bibkey>sclar-etal-2022-referee</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.655</doi>
+      <video href="2022.emnlp-main.655.mp4"/>
     </paper>
     <paper id="656">
       <title>Algorithms for Weighted Pushdown Automata</title>
@@ -8709,6 +9008,7 @@
       <attachment type="software" hash="85eb17ea">2022.emnlp-main.657.software.zip</attachment>
       <bibkey>he-etal-2022-mabel</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.657</doi>
+      <video href="2022.emnlp-main.657.mp4"/>
     </paper>
     <paper id="658">
       <title>Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs</title>
@@ -8723,6 +9023,7 @@
       <url hash="2e660292">2022.emnlp-main.658</url>
       <bibkey>richardson-etal-2022-breakpoint</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.658</doi>
+      <video href="2022.emnlp-main.658.mp4"/>
     </paper>
     <paper id="659">
       <title>Late Fusion with Triplet Margin Objective for Multimodal Ideology Prediction and Analysis</title>
@@ -8735,6 +9036,7 @@
       <url hash="b857b1c8">2022.emnlp-main.659</url>
       <bibkey>qiu-etal-2022-late</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.659</doi>
+      <video href="2022.emnlp-main.659.mp4"/>
     </paper>
     <paper id="660">
       <title>Leveraging <fixed-case>QA</fixed-case> Datasets to Improve Generative Data Augmentation</title>
@@ -8747,6 +9049,7 @@
       <url hash="622b1b20">2022.emnlp-main.660</url>
       <bibkey>mekala-etal-2022-leveraging</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.660</doi>
+      <video href="2022.emnlp-main.660.mp4"/>
     </paper>
     <paper id="661">
       <title>Meta-Learning Fast Weight Language Models</title>
@@ -8831,6 +9134,7 @@
       <url hash="a18f250a">2022.emnlp-main.667</url>
       <bibkey>balachandran-etal-2022-correcting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.667</doi>
+      <video href="2022.emnlp-main.667.mp4"/>
     </paper>
     <paper id="668">
       <title>Coordinated Topic Modeling</title>
@@ -8873,6 +9177,7 @@
       <url hash="6995b34d">2022.emnlp-main.670</url>
       <bibkey>patel-etal-2022-cripp</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.670</doi>
+      <video href="2022.emnlp-main.670.mp4"/>
     </paper>
     <paper id="671">
       <title>Entity-centered Cross-document Relation Extraction</title>
@@ -8944,6 +9249,7 @@
       <url hash="1c8ca5e5">2022.emnlp-main.675</url>
       <bibkey>gatti-etal-2022-vistot</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.675</doi>
+      <video href="2022.emnlp-main.675.mp4"/>
     </paper>
     <paper id="676">
       <title>Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentation</title>
@@ -8955,6 +9261,7 @@
       <url hash="8c9958a2">2022.emnlp-main.676</url>
       <bibkey>zhang-etal-2022-generative</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.676</doi>
+      <video href="2022.emnlp-main.676.mp4"/>
     </paper>
     <paper id="677">
       <title>Symptom Identification for Interpretable Detection of Multiple Mental Disorders on Social Media</title>
@@ -8980,6 +9287,7 @@
       <url hash="bad5acf2">2022.emnlp-main.678</url>
       <bibkey>kim-etal-2022-improving</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.678</doi>
+      <video href="2022.emnlp-main.678.mp4"/>
     </paper>
     <paper id="679">
       <title><fixed-case>CONQRR</fixed-case>: Conversational Query Rewriting for Retrieval with Reinforcement Learning</title>
@@ -9008,6 +9316,7 @@
       <url hash="c3975e21">2022.emnlp-main.680</url>
       <bibkey>lee-etal-2022-specializing</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.680</doi>
+      <video href="2022.emnlp-main.680.mp4"/>
     </paper>
     <paper id="681">
       <title>A Simple Contrastive Learning Framework for Interactive Argument Pair Identification via Argument-Context Extraction</title>
@@ -9088,6 +9397,7 @@
       <url hash="f16ac797">2022.emnlp-main.686</url>
       <bibkey>nguyen-etal-2022-adaptive</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.686</doi>
+      <video href="2022.emnlp-main.686.mp4"/>
     </paper>
     <paper id="687">
       <title>Adaptive Token-level Cross-lingual Feature Mixing for Multilingual Neural Machine Translation</title>
@@ -9126,6 +9436,7 @@
       <url hash="a9870214">2022.emnlp-main.689</url>
       <bibkey>yang-etal-2022-low</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.689</doi>
+      <video href="2022.emnlp-main.689.mp4"/>
     </paper>
     <paper id="690">
       <title>Prompt-based Distribution Alignment for Domain Generalization in Text Classification</title>
@@ -9188,6 +9499,7 @@
       <url hash="203f82e5">2022.emnlp-main.694</url>
       <bibkey>li-etal-2022-human</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.694</doi>
+      <video href="2022.emnlp-main.694.mp4"/>
     </paper>
     <paper id="695">
       <title>Continual Training of Language Models for Few-Shot Learning</title>
@@ -9214,6 +9526,7 @@
       <url hash="c3ba305e">2022.emnlp-main.696</url>
       <bibkey>wu-etal-2022-dictionary</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.696</doi>
+      <video href="2022.emnlp-main.696.mp4"/>
     </paper>
     <paper id="697">
       <title>Fine-Tuning Pre-trained Transformers into Decaying Fast Weights</title>
@@ -9249,6 +9562,7 @@
       <url hash="02f7d9bc">2022.emnlp-main.699</url>
       <bibkey>shen-etal-2022-sentbs</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.699</doi>
+      <video href="2022.emnlp-main.699.mp4"/>
     </paper>
     <paper id="700">
       <title>A Fine-grained <fixed-case>C</fixed-case>hinese Software Privacy Policy Dataset for Sequence Labeling and Regulation Compliant Identification</title>
@@ -9288,6 +9602,7 @@
       <url hash="38aaa162">2022.emnlp-main.702</url>
       <bibkey>hong-etal-2022-graph</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.702</doi>
+      <video href="2022.emnlp-main.702.mp4"/>
     </paper>
     <paper id="703">
       <title><fixed-case>D</fixed-case>isco<fixed-case>S</fixed-case>ense: Commonsense Reasoning with Discourse Connectives</title>
@@ -9321,6 +9636,7 @@
       <url hash="e860c92b">2022.emnlp-main.705</url>
       <bibkey>hu-etal-2022-mocha</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.705</doi>
+      <video href="2022.emnlp-main.705.mp4"/>
     </paper>
     <paper id="706">
       <title>Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation</title>
@@ -9365,6 +9681,7 @@
       <url hash="e30f2865">2022.emnlp-main.708</url>
       <bibkey>shen-etal-2022-mask</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.708</doi>
+      <video href="2022.emnlp-main.708.mp4"/>
     </paper>
     <paper id="709">
       <title><fixed-case>AMAL</fixed-case>: Meta Knowledge-Driven Few-Shot Adapter Learning</title>
@@ -9412,6 +9729,7 @@
       <url hash="a5c24f9d">2022.emnlp-main.712</url>
       <bibkey>kuribayashi-etal-2022-context</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.712</doi>
+      <video href="2022.emnlp-main.712.mp4"/>
     </paper>
     <paper id="713">
       <title>A Generative Model for End-to-End Argument Mining with Reconstructed Positional Encoding and Constrained Pointer Mechanism</title>
@@ -9477,6 +9795,7 @@
       <url hash="ee667482">2022.emnlp-main.716</url>
       <bibkey>mirchandani-etal-2022-fad</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.716</doi>
+      <video href="2022.emnlp-main.716.mp4"/>
     </paper>
     <paper id="717">
       <title><fixed-case>MM</fixed-case>-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences</title>
@@ -9506,6 +9825,7 @@
       <url hash="39359119">2022.emnlp-main.718</url>
       <bibkey>moon-etal-2022-evaluating</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.718</doi>
+      <video href="2022.emnlp-main.718.mp4"/>
     </paper>
     <paper id="719">
       <title><fixed-case>M</fixed-case>o<fixed-case>SE</fixed-case>: Modality Split and Ensemble for Multimodal Knowledge Graph Completion</title>
@@ -9569,6 +9889,7 @@
       <url hash="42c0c0fd">2022.emnlp-main.723</url>
       <bibkey>sun-etal-2022-reorder</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.723</doi>
+      <video href="2022.emnlp-main.723.mp4"/>
     </paper>
     <paper id="724">
       <title>Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature</title>
@@ -9615,6 +9936,7 @@
       <url hash="c542905a">2022.emnlp-main.727</url>
       <bibkey>zerveas-etal-2022-coder</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.727</doi>
+      <video href="2022.emnlp-main.727.mp4"/>
     </paper>
     <paper id="728">
       <title><fixed-case>A</fixed-case>dapter<fixed-case>S</fixed-case>hare: Task Correlation Modeling with Adapter Differentiation</title>
@@ -9689,6 +10011,7 @@
       <attachment type="software" hash="75c6a7fc">2022.emnlp-main.733.software.zip</attachment>
       <bibkey>lee-etal-2022-pneg</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.733</doi>
+      <video href="2022.emnlp-main.733.mp4"/>
     </paper>
     <paper id="734">
       <title>Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations</title>
@@ -9722,6 +10045,7 @@
       <url hash="07530599">2022.emnlp-main.736</url>
       <bibkey>schmidt-etal-2022-dont</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.736</doi>
+      <video href="2022.emnlp-main.736.mp4"/>
     </paper>
     <paper id="737">
       <title>Towards Compositional Generalization in Code Search</title>
@@ -9764,6 +10088,7 @@
       <url hash="5ee44138">2022.emnlp-main.739</url>
       <bibkey>raghu-etal-2022-structural</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.739</doi>
+      <video href="2022.emnlp-main.739.mp4"/>
     </paper>
     <paper id="740">
       <title><fixed-case>SLICER</fixed-case>: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity Recognition</title>
@@ -9775,6 +10100,7 @@
       <url hash="e2ff9715">2022.emnlp-main.740</url>
       <bibkey>schmidt-etal-2022-slicer</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.740</doi>
+      <video href="2022.emnlp-main.740.mp4"/>
     </paper>
     <paper id="741">
       <title><fixed-case>E</fixed-case>dge<fixed-case>F</fixed-case>ormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation</title>
@@ -9827,6 +10153,7 @@
       <attachment type="software" hash="1232145b">2022.emnlp-main.744.software.zip</attachment>
       <bibkey>jeong-etal-2022-kold</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.744</doi>
+      <video href="2022.emnlp-main.744.mp4"/>
     </paper>
     <paper id="745">
       <title>Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention</title>
@@ -9840,6 +10167,7 @@
       <url hash="9a4e7ecf">2022.emnlp-main.745</url>
       <bibkey>li-etal-2022-evade</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.745</doi>
+      <video href="2022.emnlp-main.745.mp4"/>
     </paper>
     <paper id="746">
       <title>The better your Syntax, the better your Semantics? Probing Pretrained Language Models for the <fixed-case>E</fixed-case>nglish Comparative Correlative</title>
@@ -9852,6 +10180,7 @@
       <url hash="ac7ead29">2022.emnlp-main.746</url>
       <bibkey>weissweiler-etal-2022-better</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.746</doi>
+      <video href="2022.emnlp-main.746.mp4"/>
     </paper>
     <paper id="747">
       <title><fixed-case>P</fixed-case>roof<fixed-case>I</fixed-case>nfer: Generating Proof via Iterative Hierarchical Inference</title>
@@ -9884,6 +10213,7 @@
       <url hash="1011d9e4">2022.emnlp-main.748</url>
       <bibkey>mukherjee-etal-2022-ectsum</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.748</doi>
+      <video href="2022.emnlp-main.748.mp4"/>
     </paper>
     <paper id="749">
       <title>Cross-domain Generalization for <fixed-case>AMR</fixed-case> Parsing</title>
@@ -9925,6 +10255,7 @@
       <url hash="aa7bd794">2022.emnlp-main.751</url>
       <bibkey>albalak-etal-2022-feta</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.751</doi>
+      <video href="2022.emnlp-main.751.mp4"/>
     </paper>
     <paper id="752">
       <title>Do Children Texts Hold The Key To Commonsense Knowledge?</title>
@@ -9947,6 +10278,7 @@
       <url hash="0edde21a">2022.emnlp-main.753</url>
       <bibkey>deutsch-etal-2022-limitations</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.753</doi>
+      <video href="2022.emnlp-main.753.mp4"/>
     </paper>
     <paper id="754">
       <title>Sampling-Based Approximations to Minimum <fixed-case>B</fixed-case>ayes Risk Decoding for Neural Machine Translation</title>
@@ -9968,6 +10300,7 @@
       <url hash="9ce790f9">2022.emnlp-main.755</url>
       <bibkey>aggarwal-etal-2022-indicxnli</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.755</doi>
+      <video href="2022.emnlp-main.755.mp4"/>
     </paper>
     <paper id="756">
       <title>Model Cascading: Towards Jointly Improving Efficiency and Accuracy of <fixed-case>NLP</fixed-case> Systems</title>
@@ -9989,6 +10322,7 @@
       <url hash="f8080267">2022.emnlp-main.757</url>
       <bibkey>jiang-etal-2022-semantic</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.757</doi>
+      <video href="2022.emnlp-main.757.mp4"/>
     </paper>
     <paper id="758">
       <title><fixed-case>XP</fixed-case>rompt: Exploring the Extreme of Prompt Tuning</title>
@@ -10030,6 +10364,7 @@
       <url hash="3b04f711">2022.emnlp-main.760</url>
       <bibkey>stengel-eskin-van-durme-2022-curious</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.760</doi>
+      <video href="2022.emnlp-main.760.mp4"/>
     </paper>
     <paper id="761">
       <title><fixed-case>SHARE</fixed-case>: a System for Hierarchical Assistive Recipe Editing</title>
@@ -10042,6 +10377,7 @@
       <url hash="79d2e1f2">2022.emnlp-main.761</url>
       <bibkey>li-etal-2022-share</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.761</doi>
+      <video href="2022.emnlp-main.761.mp4"/>
     </paper>
     <paper id="762">
       <title><fixed-case>IM</fixed-case>2: an Interpretable and Multi-category Integrated Metric Framework for Automatic Dialogue Evaluation</title>
@@ -10057,6 +10393,7 @@
       <attachment type="software" hash="79eddb5a">2022.emnlp-main.762.software.zip</attachment>
       <bibkey>jiang-etal-2022-im2</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.762</doi>
+      <video href="2022.emnlp-main.762.mp4"/>
     </paper>
     <paper id="763">
       <title><fixed-case>PEVL</fixed-case>: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models</title>
@@ -10072,6 +10409,7 @@
       <url hash="bfe99cb5">2022.emnlp-main.763</url>
       <bibkey>yao-etal-2022-pevl</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.763</doi>
+      <video href="2022.emnlp-main.763.mp4"/>
     </paper>
     <paper id="764">
       <title>Pre-training Language Models with Deterministic Factual Knowledge</title>
@@ -10088,6 +10426,7 @@
       <url hash="547d61f5">2022.emnlp-main.764</url>
       <bibkey>li-etal-2022-pre-training</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.764</doi>
+      <video href="2022.emnlp-main.764.mp4"/>
     </paper>
     <paper id="765">
       <title>Finding Skill Neurons in Pre-trained Transformer-based Language Models</title>
@@ -10102,6 +10441,7 @@
       <url hash="60b5a58e">2022.emnlp-main.765</url>
       <bibkey>wang-etal-2022-finding-skill</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.765</doi>
+      <video href="2022.emnlp-main.765.mp4"/>
     </paper>
     <paper id="766">
       <title>Prompt Conditioned <fixed-case>VAE</fixed-case>: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue</title>
@@ -10129,6 +10469,7 @@
       <url hash="bfed0c12">2022.emnlp-main.767</url>
       <bibkey>don-yehiya-etal-2022-prequel</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.767</doi>
+      <video href="2022.emnlp-main.767.mp4"/>
     </paper>
     <paper id="768">
       <title>Can Transformers Reason in Fragments of Natural Language?</title>
@@ -10140,6 +10481,7 @@
       <url hash="45e87d3a">2022.emnlp-main.768</url>
       <bibkey>schlegel-etal-2022-transformers</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.768</doi>
+      <video href="2022.emnlp-main.768.mp4"/>
     </paper>
     <paper id="769">
       <title>Textless Speech Emotion Conversion using Discrete &amp; Decomposed Representations</title>
@@ -10196,6 +10538,7 @@
       <url hash="f08605db">2022.emnlp-main.772</url>
       <bibkey>lin-byrne-2022-retrieval</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.772</doi>
+      <video href="2022.emnlp-main.772.mp4"/>
     </paper>
     <paper id="773">
       <title>Instance Regularization for Discriminative Language Model Pre-training</title>
@@ -10235,6 +10578,7 @@
       <url hash="4d63999d">2022.emnlp-main.775</url>
       <bibkey>wang-etal-2022-scienceworld</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.775</doi>
+      <video href="2022.emnlp-main.775.mp4"/>
     </paper>
     <paper id="776">
       <title>Improving Embeddings Representations for Comparing Higher Education Curricula: A Use Case in Computing</title>
@@ -10283,6 +10627,7 @@
       <attachment type="software" hash="b5a28750">2022.emnlp-main.779.software.zip</attachment>
       <bibkey>han-etal-2022-balancing</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.779</doi>
+      <video href="2022.emnlp-main.779.mp4"/>
     </paper>
     <paper id="780">
       <title>Prompting <fixed-case>ELECTRA</fixed-case>: Few-Shot Learning with Discriminative Pre-Trained Models</title>
@@ -10297,6 +10642,7 @@
       <attachment type="software" hash="849be73b">2022.emnlp-main.780.software.zip</attachment>
       <bibkey>xia-etal-2022-prompting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.780</doi>
+      <video href="2022.emnlp-main.780.mp4"/>
     </paper>
     <paper id="781">
       <title>Identifying Physical Object Use in Sentences</title>
@@ -10393,6 +10739,7 @@
       <url hash="7514164a">2022.emnlp-main.788</url>
       <bibkey>pimentel-etal-2022-attentional</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.788</doi>
+      <video href="2022.emnlp-main.788.mp4"/>
     </paper>
     <paper id="789">
       <title>When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems</title>
@@ -10409,6 +10756,7 @@
       <url hash="f263f979">2022.emnlp-main.789</url>
       <bibkey>stengel-eskin-etal-2022-data</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.789</doi>
+      <video href="2022.emnlp-main.789.mp4"/>
     </paper>
     <paper id="790">
       <title>Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt</title>
@@ -10435,6 +10783,7 @@
       <url hash="2cc5ba98">2022.emnlp-main.791</url>
       <bibkey>pujari-etal-2022-three</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.791</doi>
+      <video href="2022.emnlp-main.791.mp4"/>
     </paper>
     <paper id="792">
       <title>Topic Modeling With Topological Data Analysis</title>
@@ -10459,6 +10808,7 @@
       <attachment type="software" hash="7e6985fa">2022.emnlp-main.793.software.zip</attachment>
       <bibkey>zhu-etal-2022-predicting</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.793</doi>
+      <video href="2022.emnlp-main.793.mp4"/>
     </paper>
     <paper id="794">
       <title>Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-<fixed-case>SQL</fixed-case> Parsers</title>
@@ -10482,6 +10832,7 @@
       <url hash="c9f00662">2022.emnlp-main.795</url>
       <bibkey>sancheti-etal-2022-agent</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.795</doi>
+      <video href="2022.emnlp-main.795.mp4"/>
     </paper>
     <paper id="796">
       <title><fixed-case>COLD</fixed-case>: A Benchmark for <fixed-case>C</fixed-case>hinese Offensive Language Detection</title>
@@ -10578,6 +10929,7 @@
       <attachment type="software" hash="cd6052b1">2022.emnlp-main.802.software.zip</attachment>
       <bibkey>ostendorff-etal-2022-neighborhood</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.802</doi>
+      <video href="2022.emnlp-main.802.mp4"/>
     </paper>
     <paper id="803">
       <title><fixed-case>SPE</fixed-case>: Symmetrical Prompt Enhancement for Fact Probing</title>
@@ -10592,6 +10944,7 @@
       <url hash="7b7abfb3">2022.emnlp-main.803</url>
       <bibkey>li-etal-2022-spe</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.803</doi>
+      <video href="2022.emnlp-main.803.mp4"/>
     </paper>
     <paper id="804">
       <title>Efficient Large Scale Language Modeling with Mixtures of Experts</title>
@@ -10651,6 +11004,7 @@
       <url hash="dd52a8c9">2022.emnlp-main.806</url>
       <bibkey>ko-etal-2022-discourse</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.806</doi>
+      <video href="2022.emnlp-main.806.mp4"/>
     </paper>
     <paper id="807">
       <title>Learning to Generate Overlap Summaries through Noisy Synthetic Data</title>
@@ -10673,6 +11027,7 @@
       <url hash="9c8f1859">2022.emnlp-main.808</url>
       <bibkey>jiang-etal-2022-mutual</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.808</doi>
+      <video href="2022.emnlp-main.808.mp4"/>
     </paper>
     <paper id="809">
       <title>Directions for <fixed-case>NLP</fixed-case> Practices Applied to Online Hate Speech Detection</title>
@@ -10685,6 +11040,7 @@
       <url hash="f92f8994">2022.emnlp-main.809</url>
       <bibkey>fortuna-etal-2022-directions</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.809</doi>
+      <video href="2022.emnlp-main.809.mp4"/>
     </paper>
     <paper id="810">
       <title>Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection</title>
@@ -10697,6 +11053,7 @@
       <url hash="9e3ce857">2022.emnlp-main.810</url>
       <bibkey>di-liello-etal-2022-pre</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.810</doi>
+      <video href="2022.emnlp-main.810.mp4"/>
     </paper>
     <paper id="811">
       <title><fixed-case>O</fixed-case>pen<fixed-case>CQA</fixed-case>: Open-ended Question Answering with Charts</title>
@@ -10711,6 +11068,7 @@
       <url hash="9d335f0b">2022.emnlp-main.811</url>
       <bibkey>kantharaj-etal-2022-opencqa</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.811</doi>
+      <video href="2022.emnlp-main.811.mp4"/>
     </paper>
     <paper id="812">
       <title>A Systematic Investigation of Commonsense Knowledge in Large Language Models</title>
@@ -10725,6 +11083,7 @@
       <url hash="b6f3f3ad">2022.emnlp-main.812</url>
       <bibkey>li-etal-2022-systematic</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.812</doi>
+      <video href="2022.emnlp-main.812.mp4"/>
     </paper>
     <paper id="813">
       <title>Transforming Sequence Tagging Into A <fixed-case>S</fixed-case>eq2<fixed-case>S</fixed-case>eq Task</title>
@@ -10739,6 +11098,7 @@
       <url hash="ab0908e1">2022.emnlp-main.813</url>
       <bibkey>raman-etal-2022-transforming</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.813</doi>
+      <video href="2022.emnlp-main.813.mp4"/>
     </paper>
     <paper id="814">
       <title><fixed-case>C</fixed-case>ycle<fixed-case>KQR</fixed-case>: Unsupervised Bidirectional Keyword-Question Rewriting</title>
@@ -10855,6 +11215,7 @@
       <url hash="323d2baa">2022.emnlp-main.822</url>
       <bibkey>hangya-etal-2022-improving</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.822</doi>
+      <video href="2022.emnlp-main.822.mp4"/>
     </paper>
     <paper id="823">
       <title><fixed-case>SCROLLS</fixed-case>: Standardized <fixed-case>C</fixed-case>ompa<fixed-case>R</fixed-case>ison Over Long Language Sequences</title>
@@ -10874,6 +11235,7 @@
       <url hash="36ec1a23">2022.emnlp-main.823</url>
       <bibkey>shaham-etal-2022-scrolls</bibkey>
       <doi>10.18653/v1/2022.emnlp-main.823</doi>
+      <video href="2022.emnlp-main.823.mp4"/>
     </paper>
     <paper id="824">
       <title><fixed-case>PAR</fixed-case>: Political Actor Representation Learning with Social Context and Expert Knowledge</title>
@@ -10972,6 +11334,7 @@
       <url hash="2dc6d8c1">2022.emnlp-tutorials.1</url>
       <bibkey>flanigan-etal-2022-meaning</bibkey>
       <doi>10.18653/v1/2022.emnlp-tutorials.1</doi>
+      <video href="2022.emnlp-tutorials.1.mp4"/>
     </paper>
     <paper id="2">
       <title><fixed-case>A</fixed-case>rabic Natural Language Processing</title>
@@ -10981,6 +11344,7 @@
       <url hash="e3d42215">2022.emnlp-tutorials.2</url>
       <bibkey>habash-2022-arabic</bibkey>
       <doi>10.18653/v1/2022.emnlp-tutorials.2</doi>
+      <video href="2022.emnlp-tutorials.2.mp4"/>
     </paper>
     <paper id="3">
       <title>Emergent Language-Based Coordination In Deep Multi-Agent Systems</title>
@@ -10992,6 +11356,7 @@
       <url hash="538a9716">2022.emnlp-tutorials.3</url>
       <bibkey>baroni-etal-2022-emergent</bibkey>
       <doi>10.18653/v1/2022.emnlp-tutorials.3</doi>
+      <video href="2022.emnlp-tutorials.3.mp4"/>
     </paper>
     <paper id="4">
       <title><fixed-case>C</fixed-case>ausal<fixed-case>NLP</fixed-case> Tutorial: An Introduction to Causality for Natural Language Processing</title>
@@ -11003,6 +11368,7 @@
       <url hash="ae117c13">2022.emnlp-tutorials.4</url>
       <bibkey>jin-etal-2022-causalnlp</bibkey>
       <doi>10.18653/v1/2022.emnlp-tutorials.4</doi>
+      <video href="2022.emnlp-tutorials.4.mp4"/>
     </paper>
     <paper id="5">
       <title>Modular and Parameter-Efficient Fine-Tuning for <fixed-case>NLP</fixed-case> Models</title>
@@ -11014,6 +11380,7 @@
       <url hash="da0cdf28">2022.emnlp-tutorials.5</url>
       <bibkey>ruder-etal-2022-modular</bibkey>
       <doi>10.18653/v1/2022.emnlp-tutorials.5</doi>
+      <video href="2022.emnlp-tutorials.5.mp4"/>
     </paper>
     <paper id="6">
       <title>Non-Autoregressive Models for Fast Sequence Generation</title>
@@ -11024,6 +11391,7 @@
       <url hash="73979d2a">2022.emnlp-tutorials.6</url>
       <bibkey>feng-shao-2022-non</bibkey>
       <doi>10.18653/v1/2022.emnlp-tutorials.6</doi>
+      <video href="2022.emnlp-tutorials.6.mp4"/>
     </paper>
   </volume>
   <volume id="demos" ingest-date="2023-02-02" type="proceedings">
@@ -11058,6 +11426,7 @@
       <url hash="b36e14ef">2022.emnlp-demos.1</url>
       <bibkey>jin-etal-2022-cogktr</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.1</doi>
+      <video href="2022.emnlp-demos.1.mp4"/>
     </paper>
     <paper id="2">
       <title><fixed-case>LM</fixed-case>-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models</title>
@@ -11074,6 +11443,7 @@
       <url hash="1b22713f">2022.emnlp-demos.2</url>
       <bibkey>geva-etal-2022-lm</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.2</doi>
+      <video href="2022.emnlp-demos.2.mp4"/>
     </paper>
     <paper id="3">
       <title><fixed-case>E</fixed-case>asy<fixed-case>NLP</fixed-case>: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing</title>
@@ -11091,6 +11461,7 @@
       <url hash="abae3967">2022.emnlp-demos.3</url>
       <bibkey>wang-etal-2022-easynlp</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.3</doi>
+      <video href="2022.emnlp-demos.3.mp4"/>
     </paper>
     <paper id="4">
       <title>An Explainable Toolbox for Evaluating Pre-trained Vision-Language Models</title>
@@ -11106,6 +11477,7 @@
       <url hash="ad7c287a">2022.emnlp-demos.4</url>
       <bibkey>zhao-etal-2022-explainable</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.4</doi>
+      <video href="2022.emnlp-demos.4.mp4"/>
     </paper>
     <paper id="5">
       <title><fixed-case>T</fixed-case>weet<fixed-case>NLP</fixed-case>: Cutting-Edge Natural Language Processing for Social Media</title>
@@ -11124,6 +11496,7 @@
       <url hash="57f8f330">2022.emnlp-demos.5</url>
       <bibkey>camacho-collados-etal-2022-tweetnlp</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.5</doi>
+      <video href="2022.emnlp-demos.5.mp4"/>
     </paper>
     <paper id="6">
       <title><fixed-case>J</fixed-case>oey<fixed-case>S</fixed-case>2<fixed-case>T</fixed-case>: Minimalistic Speech-to-Text Modeling with <fixed-case>J</fixed-case>oey<fixed-case>NMT</fixed-case></title>
@@ -11135,6 +11508,7 @@
       <bibkey>ohta-etal-2022-joeys2t</bibkey>
       <abstract>JoeyS2T is a JoeyNMT extension for speech-to-text tasks such as automatic speech recognition and end-to-end speech translation. It inherits the core philosophy of JoeyNMT, a minimalist NMT toolkit built on PyTorch, seeking simplicity and accessibility. JoeyS2T’s workflow is self-contained, starting from data pre-processing, over model training and prediction to evaluation, and is seamlessly integrated into JoeyNMT’s compact and simple code base. On top of JoeyNMT’s state-of-the-art Transformer-based Encoder-Decoder architecture, JoeyS2T provides speech-oriented components such as convolutional layers, SpecAugment, CTC-loss, and WER evaluation. Despite its simplicity compared to prior implementations, JoeyS2T performs competitively on English speech recognition and English-to-German speech translation benchmarks. The implementation is accompanied by a walk-through tutorial and available on <url>https://github.com/may-/joeys2t</url>.</abstract>
       <doi>10.18653/v1/2022.emnlp-demos.6</doi>
+      <video href="2022.emnlp-demos.6.mp4"/>
     </paper>
     <paper id="7">
       <title><fixed-case>F</fixed-case>air<fixed-case>L</fixed-case>ib: A Unified Framework for Assessing and Improving Fairness</title>
@@ -11149,6 +11523,7 @@
       <url hash="5f4511f4">2022.emnlp-demos.7</url>
       <bibkey>han-etal-2022-fairlib</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.7</doi>
+      <video href="2022.emnlp-demos.7.mp4"/>
     </paper>
     <paper id="8">
       <title><fixed-case>ELEVANT</fixed-case>: A Fully Automatic Fine-Grained Entity Linking Evaluation and Analysis Tool</title>
@@ -11160,6 +11535,7 @@
       <url hash="416c1519">2022.emnlp-demos.8</url>
       <bibkey>bast-etal-2022-elevant</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.8</doi>
+      <video href="2022.emnlp-demos.8.mp4"/>
     </paper>
     <paper id="9">
       <title>A Pipeline for Generating, Annotating and Employing Synthetic Data for Real World Question Answering</title>
@@ -11172,6 +11548,7 @@
       <url hash="c5060ba1">2022.emnlp-demos.9</url>
       <bibkey>maufe-etal-2022-pipeline</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.9</doi>
+      <video href="2022.emnlp-demos.9.mp4"/>
     </paper>
     <paper id="10">
       <title><fixed-case>D</fixed-case>eep<fixed-case>KE</fixed-case>: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population</title>
@@ -11190,6 +11567,7 @@
       <url hash="6ef4af1e">2022.emnlp-demos.10</url>
       <bibkey>zhang-etal-2022-deepke</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.10</doi>
+      <video href="2022.emnlp-demos.10.mp4"/>
     </paper>
     <paper id="11">
       <title><fixed-case>A</fixed-case>n<fixed-case>EMIC</fixed-case>: A Framework for Benchmarking <fixed-case>ICD</fixed-case> Coding Models</title>
@@ -11203,6 +11581,7 @@
       <bibkey>kim-etal-2022-anemic</bibkey>
       <abstract>Diagnostic coding, or ICD coding, is the task of assigning diagnosis codes defined by the ICD (International Classification of Diseases) standard to patient visits based on clinical notes. The current process of manual ICD coding is time-consuming and often error-prone, which suggests the need for automatic ICD coding. However, despite the long history of automatic ICD coding, there have been no standardized frameworks for benchmarking ICD coding models. We open-source an easy-to-use tool named <i>AnEMIC</i>, which provides a streamlined pipeline for preprocessing, training, and evaluating for automatic ICD coding. We correct errors in preprocessing by existing works, and provide key models and weights trained on the correctly preprocessed datasets. We also provide an interactive demo performing real-time inference from custom inputs, and visualizations drawn from explainable AI to analyze the models. We hope the framework helps move the research of ICD coding forward and helps professionals explore the potential of ICD coding. The framework and the associated code are available here.</abstract>
       <doi>10.18653/v1/2022.emnlp-demos.11</doi>
+      <video href="2022.emnlp-demos.11.mp4"/>
     </paper>
     <paper id="12">
       <title><fixed-case>SPEAR</fixed-case> : Semi-supervised Data Programming in Python</title>
@@ -11218,6 +11597,7 @@
       <url hash="cb94229e">2022.emnlp-demos.12</url>
       <bibkey>abhishek-etal-2022-spear</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.12</doi>
+      <video href="2022.emnlp-demos.12.mp4"/>
     </paper>
     <paper id="13">
       <title>Evaluate &amp; Evaluation on the Hub: Better Best Practices for Data and Model Measurements</title>
@@ -11236,6 +11616,7 @@
       <url hash="c05066e4">2022.emnlp-demos.13</url>
       <bibkey>von-werra-etal-2022-evaluate</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.13</doi>
+      <video href="2022.emnlp-demos.13.mp4"/>
     </paper>
     <paper id="14">
       <title><fixed-case>K</fixed-case>eyword<fixed-case>S</fixed-case>cape: Visual Document Exploration using Contextualized Keyword Embeddings</title>
@@ -11248,6 +11629,7 @@
       <url hash="cbb7995f">2022.emnlp-demos.14</url>
       <bibkey>voigt-etal-2022-keywordscape</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.14</doi>
+      <video href="2022.emnlp-demos.14.mp4"/>
     </paper>
     <paper id="15">
       <title><fixed-case>M</fixed-case>ed<fixed-case>C</fixed-case>on<fixed-case>QA</fixed-case>: Medical Conversational Question Answering System based on Knowledge Graphs</title>
@@ -11264,6 +11646,7 @@
       <url hash="8a9e4c9f">2022.emnlp-demos.15</url>
       <bibkey>xia-etal-2022-medconqa</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.15</doi>
+      <video href="2022.emnlp-demos.15.mp4"/>
     </paper>
     <paper id="16">
       <title>Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours</title>
@@ -11282,6 +11665,7 @@
       <url hash="7f199c21">2022.emnlp-demos.16</url>
       <bibkey>shnarch-etal-2022-label</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.16</doi>
+      <video href="2022.emnlp-demos.16.mp4"/>
     </paper>
     <paper id="17">
       <title><fixed-case>AGR</fixed-case>e<fixed-case>E</fixed-case>: A system for generating Automated Grammar Reading Exercises</title>
@@ -11294,6 +11678,7 @@
       <url hash="a45a4788">2022.emnlp-demos.17</url>
       <bibkey>chan-etal-2022-agree</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.17</doi>
+      <video href="2022.emnlp-demos.17.mp4"/>
     </paper>
     <paper id="18">
       <title><fixed-case>B</fixed-case>ot<fixed-case>SIM</fixed-case>: An End-to-End Bot Simulation Framework for Commercial Task-Oriented Dialog Systems</title>
@@ -11308,6 +11693,7 @@
       <url hash="1f38cdf7">2022.emnlp-demos.18</url>
       <bibkey>wang-etal-2022-botsim</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.18</doi>
+      <video href="2022.emnlp-demos.18.mp4"/>
     </paper>
     <paper id="19">
       <title><fixed-case>D</fixed-case>eep<fixed-case>G</fixed-case>en: Diverse Search Ad Generation and Real-Time Customization</title>
@@ -11355,6 +11741,7 @@
       <bibkey>zhang-etal-2022-automatic-comment</bibkey>
       <abstract>Automatic essay evaluation can help reduce teachers’ workload and enable students to refine their works rapidly. Previous studies focus mainly on giving discrete scores for either the holistic quality orseveral distinct traits. However, real-world teachers usually provide detailed comments in natural language, which are more informative than single scores. In this paper, we present the comment generation task, which aims to generate commentsfor specified segments from given student narrative essays. To tackle this task, we propose a planning-based generation model, which first plans a sequence of keywords, and then expands these keywords into a complete comment. To improve the correctness and informativeness of generated comments, we adopt two following techniques: (1) training an error correction module to filter out incorrect keywords, and (2) recognizing fine-grained structured features from source essays to enrich the keywords. To support the evaluation of the task, we collect a human-written Chinese dataset, which contains 22,399 essay-comment pairs. Extensive experiments show that our model outperforms strong baselines significantly. Moreover, we exert explicit control on our model to generate comments to describe the strengths or weaknesses of inputs with a 91% success rate. We deploy the model at <url>http://coai.cs.tsinghua.edu.cn/static/essayComment/</url>. A demo video is available at <url>https://youtu.be/IuFVk8dUxbI</url>. Our code and data are available at <url>https://github.com/thu-coai/EssayCommentGen</url>.</abstract>
       <doi>10.18653/v1/2022.emnlp-demos.21</doi>
+      <video href="2022.emnlp-demos.21.mp4"/>
     </paper>
     <paper id="22">
       <title><fixed-case>MIC</fixed-case>: A Multi-task Interactive Curation Tool</title>
@@ -11367,6 +11754,7 @@
       <url hash="062a8583">2022.emnlp-demos.22</url>
       <bibkey>yu-etal-2022-mic</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.22</doi>
+      <video href="2022.emnlp-demos.22.mp4"/>
     </paper>
     <paper id="23">
       <title><fixed-case>SUMMARY</fixed-case> <fixed-case>WORKBENCH</fixed-case>: Unifying Application and Evaluation of Text Summarization Models</title>
@@ -11378,6 +11766,7 @@
       <url hash="cee65fb8">2022.emnlp-demos.23</url>
       <bibkey>syed-etal-2022-summary</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.23</doi>
+      <video href="2022.emnlp-demos.23.mp4"/>
     </paper>
     <paper id="24">
       <title><fixed-case>A</fixed-case>rabic Word-level Readability Visualization for Assisted Text Simplification</title>
@@ -11391,6 +11780,7 @@
       <url hash="ffd0971a">2022.emnlp-demos.24</url>
       <bibkey>hazim-etal-2022-arabic</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.24</doi>
+      <video href="2022.emnlp-demos.24.mp4"/>
     </paper>
     <paper id="25">
       <title><fixed-case>L</fixed-case>ogi<fixed-case>T</fixed-case>orch: A <fixed-case>P</fixed-case>y<fixed-case>T</fixed-case>orch-based library for logical reasoning on natural language</title>
@@ -11402,6 +11792,7 @@
       <url hash="d772ab2f">2022.emnlp-demos.25</url>
       <bibkey>helwe-etal-2022-logitorch</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.25</doi>
+      <video href="2022.emnlp-demos.25.mp4"/>
     </paper>
     <paper id="26">
       <title>stopes - Modular Machine Translation Pipelines</title>
@@ -11420,6 +11811,7 @@
       <url hash="7ad05287">2022.emnlp-demos.26</url>
       <bibkey>andrews-etal-2022-stopes</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.26</doi>
+      <video href="2022.emnlp-demos.26.mp4"/>
     </paper>
     <paper id="27">
       <title><fixed-case>GEM</fixed-case>v2: Multilingual <fixed-case>NLG</fixed-case> Benchmarking in a Single Line of Code</title>
@@ -11529,6 +11921,7 @@
       <url hash="0f6b3514">2022.emnlp-demos.29</url>
       <bibkey>bianchi-etal-2022-twitter</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.29</doi>
+      <video href="2022.emnlp-demos.29.mp4"/>
     </paper>
     <paper id="30">
       <title>Azimuth: Systematic Error Analysis for Text Classification</title>
@@ -11545,6 +11938,7 @@
       <url hash="95459681">2022.emnlp-demos.30</url>
       <bibkey>gauthier-melancon-etal-2022-azimuth</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.30</doi>
+      <video href="2022.emnlp-demos.30.mp4"/>
     </paper>
     <paper id="31">
       <title><fixed-case>S</fixed-case>yn<fixed-case>KB</fixed-case>: Semantic Search for Synthetic Procedures</title>
@@ -11558,6 +11952,7 @@
       <url hash="1ae3ca13">2022.emnlp-demos.31</url>
       <bibkey>bai-etal-2022-synkb</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.31</doi>
+      <video href="2022.emnlp-demos.31.mp4"/>
     </paper>
     <paper id="32">
       <title>Camelira: An <fixed-case>A</fixed-case>rabic Multi-Dialect Morphological Disambiguator</title>
@@ -11569,6 +11964,7 @@
       <url hash="e74d4263">2022.emnlp-demos.32</url>
       <bibkey>obeid-etal-2022-camelira</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.32</doi>
+      <video href="2022.emnlp-demos.32.mp4"/>
     </paper>
     <paper id="33">
       <title><fixed-case>POTATO</fixed-case>: The Portable Text Annotation Tool</title>
@@ -11584,6 +11980,7 @@
       <url hash="0388e0c2">2022.emnlp-demos.33</url>
       <bibkey>pei-etal-2022-potato</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.33</doi>
+      <video href="2022.emnlp-demos.33.mp4"/>
     </paper>
     <paper id="34">
       <title><fixed-case>KG</fixed-case>x<fixed-case>B</fixed-case>oard: Explainable and Interactive Leaderboard for Evaluation of Knowledge Graph Completion Models</title>
@@ -11600,6 +11997,7 @@
       <url hash="d76bdcfd">2022.emnlp-demos.34</url>
       <bibkey>widjaja-etal-2022-kgxboard</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.34</doi>
+      <video href="2022.emnlp-demos.34.mp4"/>
     </paper>
     <paper id="35">
       <title><fixed-case>FALTE</fixed-case>: A Toolkit for Fine-grained Annotation for Long Text Evaluation</title>
@@ -11611,6 +12009,7 @@
       <url hash="2024d2b0">2022.emnlp-demos.35</url>
       <bibkey>goyal-etal-2022-falte</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.35</doi>
+      <video href="2022.emnlp-demos.35.mp4"/>
     </paper>
     <paper id="36">
       <title><fixed-case>SEAL</fixed-case>: Interactive Tool for Systematic Error Analysis and Labeling</title>
@@ -11624,6 +12023,7 @@
       <url hash="5bf641ba">2022.emnlp-demos.36</url>
       <bibkey>rajani-etal-2022-seal</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.36</doi>
+      <video href="2022.emnlp-demos.36.mp4"/>
     </paper>
     <paper id="37">
       <title>Hands-On Interactive Neuro-Symbolic <fixed-case>NLP</fixed-case> with <fixed-case>DR</fixed-case>ai<fixed-case>L</fixed-case></title>
@@ -11635,6 +12035,7 @@
       <url hash="f7f5d7d7">2022.emnlp-demos.37</url>
       <bibkey>pacheco-etal-2022-hands</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.37</doi>
+      <video href="2022.emnlp-demos.37.mp4"/>
     </paper>
     <paper id="38">
       <title>Paraphrastic Representations at Scale</title>
@@ -11660,6 +12061,7 @@
       <url hash="f5d6161b">2022.emnlp-demos.39</url>
       <bibkey>razeghi-etal-2022-snoopy</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.39</doi>
+      <video href="2022.emnlp-demos.39.mp4"/>
     </paper>
     <paper id="40">
       <title><fixed-case>BMC</fixed-case>ook: A Task-agnostic Compression Toolkit for Big Models</title>
@@ -11677,6 +12079,7 @@
       <bibkey>zhang-etal-2022-bmcook</bibkey>
       <abstract>Recently, pre-trained language models (PLMs) have achieved great success on various NLP tasks and have shown a trend of exponential growth in model size. To alleviate the unaffordable computational costs brought by the size growth, model compression has been widely explored. Existing efforts have achieved promising results in compressing medium-sized models for specific tasks, while task-agnostic compression for big models with over billions of parameters is rarely studied. Task-agnostic compression can provide an efficient and versatile big model for both prompting and delta tuning, leading to a more general impact than task-specific compression. Hence, we introduce a task-agnostic compression toolkit BMCook for big models. In BMCook, we implement four representative compression methods, including quantization, pruning, distillation, and MoEfication. Developers can easily combine these methods towards better efficiency. To evaluate BMCook, we apply it to compress T5-3B (a PLM with 3 billion parameters). We achieve nearly 12x efficiency improvement while maintaining over 97% of the original T5-3B performance on three typical NLP benchmarks. Moreover, the final compressed model also significantly outperforms T5-base (a PLM with 220 million parameters), which has a similar computational cost. BMCook is publicly available at <url>https://github.com/OpenBMB/BMCook</url>.</abstract>
       <doi>10.18653/v1/2022.emnlp-demos.40</doi>
+      <video href="2022.emnlp-demos.40.mp4"/>
     </paper>
     <paper id="41">
       <title><fixed-case>ALT</fixed-case>oolbox: A Set of Tools for Active Learning Annotation of Natural Language Texts</title>
@@ -11698,6 +12101,7 @@
       <url hash="945bbfad">2022.emnlp-demos.41</url>
       <bibkey>tsvigun-etal-2022-altoolbox</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.41</doi>
+      <video href="2022.emnlp-demos.41.mp4"/>
     </paper>
     <paper id="42">
       <title><fixed-case>T</fixed-case>ext<fixed-case>B</fixed-case>ox 2.0: A Text Generation Library with Pre-trained Language Models</title>
@@ -11715,6 +12119,7 @@
       <url hash="39b11371">2022.emnlp-demos.42</url>
       <bibkey>tang-etal-2022-textbox</bibkey>
       <doi>10.18653/v1/2022.emnlp-demos.42</doi>
+      <video href="2022.emnlp-demos.42.mp4"/>
     </paper>
   </volume>
   <volume id="industry" ingest-date="2023-03-11" type="proceedings">
@@ -11743,6 +12148,7 @@
       <url hash="098d8f66">2022.emnlp-industry.1</url>
       <bibkey>fusco-etal-2022-unsupervised</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.1</doi>
+      <video href="2022.emnlp-industry.1.mp4"/>
     </paper>
     <paper id="2">
       <title><fixed-case>D</fixed-case>yna<fixed-case>M</fixed-case>a<fixed-case>R</fixed-case>: Dynamic Prompt with Mask Token Representation</title>
@@ -11759,6 +12165,7 @@
       <url hash="05e805cf">2022.emnlp-industry.2</url>
       <bibkey>sun-etal-2022-dynamar</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.2</doi>
+      <video href="2022.emnlp-industry.2.mp4"/>
     </paper>
     <paper id="3">
       <title>A Hybrid Approach to Cross-lingual Product Review Summarization</title>
@@ -11771,6 +12178,7 @@
       <url hash="4befb3cd">2022.emnlp-industry.3</url>
       <bibkey>soltan-etal-2022-hybrid</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.3</doi>
+      <video href="2022.emnlp-industry.3.mp4"/>
     </paper>
     <paper id="4">
       <title>Augmenting Operations Research with Auto-Formulation of Optimization Models From Problem Descriptions</title>
@@ -11787,6 +12195,7 @@
       <url hash="b447ee76">2022.emnlp-industry.4</url>
       <bibkey>ramamonjison-etal-2022-augmenting</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.4</doi>
+      <video href="2022.emnlp-industry.4.mp4"/>
     </paper>
     <paper id="5">
       <title>Knowledge Distillation based Contextual Relevance Matching for <fixed-case>E</fixed-case>-commerce Product Search</title>
@@ -11800,6 +12209,7 @@
       <url hash="d89bd5d4">2022.emnlp-industry.5</url>
       <bibkey>liu-etal-2022-knowledge</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.5</doi>
+      <video href="2022.emnlp-industry.5.mp4"/>
     </paper>
     <paper id="6">
       <title>Accelerating the Discovery of Semantic Associations from Medical Literature: Mining Relations Between Diseases and Symptoms</title>
@@ -11811,6 +12221,7 @@
       <url hash="98afeb29">2022.emnlp-industry.6</url>
       <bibkey>purpura-etal-2022-accelerating</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.6</doi>
+      <video href="2022.emnlp-industry.6.mp4"/>
     </paper>
     <paper id="7">
       <title><fixed-case>PENTATRON</fixed-case>: <fixed-case>PE</fixed-case>rsonalized co<fixed-case>NT</fixed-case>ext-Aware Transformer for Retrieval-based c<fixed-case>O</fixed-case>nversational u<fixed-case>N</fixed-case>derstanding</title>
@@ -11826,6 +12237,7 @@
       <url hash="e8da8e85">2022.emnlp-industry.7</url>
       <bibkey>uma-naresh-etal-2022-pentatron</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.7</doi>
+      <video href="2022.emnlp-industry.7.mp4"/>
     </paper>
     <paper id="8">
       <title>Machine translation impact in <fixed-case>E</fixed-case>-commerce multilingual search</title>
@@ -11836,6 +12248,7 @@
       <url hash="59ca64a4">2022.emnlp-industry.8</url>
       <bibkey>zhang-misra-2022-machine</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.8</doi>
+      <video href="2022.emnlp-industry.8.mp4"/>
     </paper>
     <paper id="9">
       <title>Ask-and-Verify: Span Candidate Generation and Verification for Attribute Value Extraction</title>
@@ -11850,6 +12263,7 @@
       <url hash="87e0e338">2022.emnlp-industry.9</url>
       <bibkey>ding-etal-2022-ask</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.9</doi>
+      <video href="2022.emnlp-industry.9.mp4"/>
     </paper>
     <paper id="10">
       <title>Consultation Checklists: Standardising the Human Evaluation of Medical Note Generation</title>
@@ -11864,6 +12278,7 @@
       <url hash="c9dcbdf3">2022.emnlp-industry.10</url>
       <bibkey>savkov-etal-2022-consultation</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.10</doi>
+      <video href="2022.emnlp-industry.10.mp4"/>
     </paper>
     <paper id="11">
       <title>Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned?</title>
@@ -11876,6 +12291,7 @@
       <url hash="61444174">2022.emnlp-industry.11</url>
       <bibkey>do-etal-2022-towards</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.11</doi>
+      <video href="2022.emnlp-industry.11.mp4"/>
     </paper>
     <paper id="12">
       <title>Knowledge Distillation Transfer Sets and their Impact on Downstream <fixed-case>NLU</fixed-case> Tasks</title>
@@ -11890,6 +12306,7 @@
       <url hash="fe9b44b3">2022.emnlp-industry.12</url>
       <bibkey>peris-etal-2022-knowledge</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.12</doi>
+      <video href="2022.emnlp-industry.12.mp4"/>
     </paper>
     <paper id="13">
       <title>Exploiting In-Domain Bilingual Corpora for Zero-Shot Transfer Learning in <fixed-case>NLU</fixed-case> of Intra-Sentential Code-Switching Chatbot Interactions</title>
@@ -11904,6 +12321,7 @@
       <url hash="64ee9152">2022.emnlp-industry.13</url>
       <bibkey>aguirre-etal-2022-exploiting</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.13</doi>
+      <video href="2022.emnlp-industry.13.mp4"/>
     </paper>
     <paper id="14">
       <title>Calibrating Imbalanced Classifiers with Focal Loss: An Empirical Study</title>
@@ -11918,6 +12336,7 @@
       <bibkey>wang-etal-2022-calibrating</bibkey>
       <abstract>Imbalanced data distribution is a practical and common challenge in building production-level machine learning (ML) models in industry, where data usually exhibits long-tail distributions. For instance, in virtual AI Assistants, such as Google Assistant, Amazon Alexa and Apple Siri, the “play music” or “set timer” utterance is exposed to an order of magnitude more traffic than other skills. This can easily cause trained models to overfit to the majority classes, categories or intents, lead to model miscalibration. The uncalibrated models output unreliable (mostly overconfident) predictions, which are at high risk of affecting downstream decision-making systems. In this work, we study the calibration of production models in the industry use-case of predicting product return reason codes in customer service conversations of an online retail store; The returns reasons also exhibit class imbalance. To alleviate the resulting miscalibration in the production ML model, we streamline the model development and deployment using focal loss (CITATION).We empirically show the effectiveness of model training with focal loss in learning better calibrated models, as compared to standard cross-entropy loss. Better calibration, in turn, enables better control of the precision-recall trade-off for the models deployed in production.</abstract>
       <doi>10.18653/v1/2022.emnlp-industry.14</doi>
+      <video href="2022.emnlp-industry.14.mp4"/>
     </paper>
     <paper id="15">
       <title>Unsupervised training data re-weighting for natural language understanding with local distribution approximation</title>
@@ -11931,6 +12350,7 @@
       <url hash="56e7e36e">2022.emnlp-industry.15</url>
       <bibkey>garrido-ramas-etal-2022-unsupervised</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.15</doi>
+      <video href="2022.emnlp-industry.15.mp4"/>
     </paper>
     <paper id="16">
       <title>Cross-Encoder Data Annotation for Bi-Encoder Based Product Matching</title>
@@ -11941,6 +12361,7 @@
       <url hash="e9b801d0">2022.emnlp-industry.16</url>
       <bibkey>chiu-shinzato-2022-cross</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.16</doi>
+      <video href="2022.emnlp-industry.16.mp4"/>
     </paper>
     <paper id="17">
       <title>Deploying a Retrieval based Response Model for Task Oriented Dialogues</title>
@@ -11955,6 +12376,7 @@
       <url hash="630c2b33">2022.emnlp-industry.17</url>
       <bibkey>poddar-etal-2022-deploying</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.17</doi>
+      <video href="2022.emnlp-industry.17.mp4"/>
     </paper>
     <paper id="18">
       <title>Tackling Temporal Questions in Natural Language Interface to Databases</title>
@@ -11967,6 +12389,7 @@
       <url hash="9b7f7a07">2022.emnlp-industry.18</url>
       <bibkey>vo-etal-2022-tackling</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.18</doi>
+      <video href="2022.emnlp-industry.18.mp4"/>
     </paper>
     <paper id="19">
       <title>Multi-Tenant Optimization For Few-Shot Task-Oriented <fixed-case>FAQ</fixed-case> Retrieval</title>
@@ -11979,6 +12402,7 @@
       <url hash="ba6a6155">2022.emnlp-industry.19</url>
       <bibkey>vishwanathan-etal-2022-multi</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.19</doi>
+      <video href="2022.emnlp-industry.19.mp4"/>
     </paper>
     <paper id="20">
       <title>Iterative Stratified Testing and Measurement for Automated Model Updates</title>
@@ -11995,6 +12419,7 @@
       <url hash="fb9e59fa">2022.emnlp-industry.20</url>
       <bibkey>dekeyser-etal-2022-iterative</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.20</doi>
+      <video href="2022.emnlp-industry.20.mp4"/>
     </paper>
     <paper id="21">
       <title><fixed-case>SLATE</fixed-case>: A Sequence Labeling Approach for Task Extraction from Free-form Inked Content</title>
@@ -12013,6 +12438,7 @@
       <url hash="26420df1">2022.emnlp-industry.21</url>
       <bibkey>gandhi-etal-2022-slate</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.21</doi>
+      <video href="2022.emnlp-industry.21.mp4"/>
     </paper>
     <paper id="22">
       <title>Gaining Insights into Unrecognized User Utterances in Task-Oriented Dialog Systems</title>
@@ -12027,6 +12453,7 @@
       <url hash="695d8c89">2022.emnlp-industry.22</url>
       <bibkey>rabinovich-etal-2022-gaining</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.22</doi>
+      <video href="2022.emnlp-industry.22.mp4"/>
     </paper>
     <paper id="23">
       <title><fixed-case>C</fixed-case>o<fixed-case>C</fixed-case>o<fixed-case>ID</fixed-case>: Learning Contrastive Representations and Compact Clusters for Semi-Supervised Intent Discovery</title>
@@ -12039,6 +12466,7 @@
       <url hash="5f0eda52">2022.emnlp-industry.23</url>
       <bibkey>cao-etal-2022-cocoid</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.23</doi>
+      <video href="2022.emnlp-industry.23.mp4"/>
     </paper>
     <paper id="24">
       <title>Tractable &amp; Coherent Multi-Document Summarization: Discrete Optimization of Multiple Neural Modeling Streams via Integer Linear Programming</title>
@@ -12049,6 +12477,7 @@
       <url hash="089268e5">2022.emnlp-industry.24</url>
       <bibkey>j-kurisinkel-chen-2022-tractable</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.24</doi>
+      <video href="2022.emnlp-industry.24.mp4"/>
     </paper>
     <paper id="25">
       <title>Grafting Pre-trained Models for Multimodal Headline Generation</title>
@@ -12063,6 +12492,7 @@
       <url hash="f39f4943">2022.emnlp-industry.25</url>
       <bibkey>qiao-etal-2022-grafting</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.25</doi>
+      <video href="2022.emnlp-industry.25.mp4"/>
     </paper>
     <paper id="26">
       <title>Semi-supervised Adversarial Text Generation based on <fixed-case>S</fixed-case>eq2<fixed-case>S</fixed-case>eq models</title>
@@ -12078,6 +12508,7 @@
       <url hash="8c617f13">2022.emnlp-industry.26</url>
       <bibkey>le-etal-2022-semi</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.26</doi>
+      <video href="2022.emnlp-industry.26.mp4"/>
     </paper>
     <paper id="27">
       <title>Is it out yet? Automatic Future Product Releases Extraction from Web Data</title>
@@ -12089,6 +12520,7 @@
       <url hash="15d969a8">2022.emnlp-industry.27</url>
       <bibkey>fuchs-etal-2022-yet</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.27</doi>
+      <video href="2022.emnlp-industry.27.mp4"/>
     </paper>
     <paper id="28">
       <title>Automatic Scene-based Topic Channel Construction System for <fixed-case>E</fixed-case>-Commerce</title>
@@ -12103,6 +12535,7 @@
       <url hash="aa8c0726">2022.emnlp-industry.28</url>
       <bibkey>lin-etal-2022-automatic-scene</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.28</doi>
+      <video href="2022.emnlp-industry.28.mp4"/>
     </paper>
     <paper id="29">
       <title><fixed-case>S</fixed-case>peech<fixed-case>N</fixed-case>et: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale</title>
@@ -12121,6 +12554,7 @@
       <url hash="b69df9b1">2022.emnlp-industry.29</url>
       <bibkey>tang-etal-2022-speechnet</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.29</doi>
+      <video href="2022.emnlp-industry.29.mp4"/>
     </paper>
     <paper id="30">
       <title>Controlled Language Generation for Language Learning Items</title>
@@ -12132,6 +12566,7 @@
       <url hash="df789c3d">2022.emnlp-industry.30</url>
       <bibkey>stowe-etal-2022-controlled</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.30</doi>
+      <video href="2022.emnlp-industry.30.mp4"/>
     </paper>
     <paper id="31">
       <title>Improving Text-to-<fixed-case>SQL</fixed-case> Semantic Parsing with Fine-grained Query Understanding</title>
@@ -12148,6 +12583,7 @@
       <url hash="be49976b">2022.emnlp-industry.31</url>
       <bibkey>wang-etal-2022-improving-text</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.31</doi>
+      <video href="2022.emnlp-industry.31.mp4"/>
     </paper>
     <paper id="32">
       <title>Unsupervised Dense Retrieval for Scientific Articles</title>
@@ -12160,6 +12596,7 @@
       <url hash="a4ac883e">2022.emnlp-industry.32</url>
       <bibkey>li-etal-2022-unsupervised-dense</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.32</doi>
+      <video href="2022.emnlp-industry.32.mp4"/>
     </paper>
     <paper id="33">
       <title>Learning Geolocations for Cold-Start and Hard-to-Resolve Addresses via Deep Metric Learning</title>
@@ -12170,6 +12607,7 @@
       <url hash="333bd7f1">2022.emnlp-industry.33</url>
       <bibkey>govind-sohoney-2022-learning</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.33</doi>
+      <video href="2022.emnlp-industry.33.mp4"/>
     </paper>
     <paper id="34">
       <title>Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks</title>
@@ -12183,6 +12621,7 @@
       <url hash="404d7a26">2022.emnlp-industry.34</url>
       <bibkey>sehanobish-etal-2022-meta</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.34</doi>
+      <video href="2022.emnlp-industry.34.mp4"/>
     </paper>
     <paper id="35">
       <title>Named Entity Recognition in Industrial Tables using Tabular Language Models</title>
@@ -12196,6 +12635,7 @@
       <url hash="0b21872c">2022.emnlp-industry.35</url>
       <bibkey>koleva-etal-2022-named</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.35</doi>
+      <video href="2022.emnlp-industry.35.mp4"/>
     </paper>
     <paper id="36">
       <title>Reinforced Question Rewriting for Conversational Question Answering</title>
@@ -12210,6 +12650,7 @@
       <url hash="276b1ab0">2022.emnlp-industry.36</url>
       <bibkey>chen-etal-2022-reinforced</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.36</doi>
+      <video href="2022.emnlp-industry.36.mp4"/>
     </paper>
     <paper id="37">
       <title>Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection</title>
@@ -12226,6 +12667,7 @@
       <url hash="a646056e">2022.emnlp-industry.37</url>
       <bibkey>schroedl-etal-2022-improving</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.37</doi>
+      <video href="2022.emnlp-industry.37.mp4"/>
     </paper>
     <paper id="38">
       <title>Improving Precancerous Case Characterization via Transformer-based Ensemble Learning</title>
@@ -12242,6 +12684,7 @@
       <url hash="7dafeb91">2022.emnlp-industry.38</url>
       <bibkey>zhong-etal-2022-improving-precancerous</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.38</doi>
+      <video href="2022.emnlp-industry.38.mp4"/>
     </paper>
     <paper id="39">
       <title>Developing Prefix-Tuning Models for Hierarchical Text Classification</title>
@@ -12253,6 +12696,7 @@
       <url hash="02b5d578">2022.emnlp-industry.39</url>
       <bibkey>chen-etal-2022-developing</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.39</doi>
+      <video href="2022.emnlp-industry.39.mp4"/>
     </paper>
     <paper id="40">
       <title><fixed-case>PAIGE</fixed-case>: Personalized Adaptive Interactions Graph Encoder for Query Rewriting in Dialogue Systems</title>
@@ -12266,6 +12710,7 @@
       <url hash="0a00d109">2022.emnlp-industry.40</url>
       <bibkey>bis-etal-2022-paige</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.40</doi>
+      <video href="2022.emnlp-industry.40.mp4"/>
     </paper>
     <paper id="41">
       <title>Fast Vocabulary Transfer for Language Model Compression</title>
@@ -12278,6 +12723,7 @@
       <url hash="9c7edb8e">2022.emnlp-industry.41</url>
       <bibkey>gee-etal-2022-fast</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.41</doi>
+      <video href="2022.emnlp-industry.41.mp4"/>
     </paper>
     <paper id="42">
       <title>Multimodal Context Carryover</title>
@@ -12296,6 +12742,7 @@
       <url hash="b147e04f">2022.emnlp-industry.42</url>
       <bibkey>wanigasekara-etal-2022-multimodal</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.42</doi>
+      <video href="2022.emnlp-industry.42.mp4"/>
     </paper>
     <paper id="43">
       <title>Distilling Multilingual Transformers into <fixed-case>CNN</fixed-case>s for Scalable Intent Classification</title>
@@ -12308,6 +12755,7 @@
       <url hash="543a0b2e">2022.emnlp-industry.43</url>
       <bibkey>fetahu-etal-2022-distilling</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.43</doi>
+      <video href="2022.emnlp-industry.43.mp4"/>
     </paper>
     <paper id="44">
       <title>Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support</title>
@@ -12326,6 +12774,7 @@
       <url hash="550080f4">2022.emnlp-industry.44</url>
       <bibkey>obadinma-etal-2022-bringing</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.44</doi>
+      <video href="2022.emnlp-industry.44.mp4"/>
     </paper>
     <paper id="45">
       <title>Zero-Shot Dynamic Quantization for Transformer Inference</title>
@@ -12337,6 +12786,7 @@
       <url hash="1bc70fe8">2022.emnlp-industry.45</url>
       <bibkey>el-kurdi-etal-2022-zero</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.45</doi>
+      <video href="2022.emnlp-industry.45.mp4"/>
     </paper>
     <paper id="46">
       <title>Fact Checking Machine Generated Text with Dependency Trees</title>
@@ -12350,6 +12800,7 @@
       <url hash="39d0df27">2022.emnlp-industry.46</url>
       <bibkey>estes-etal-2022-fact</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.46</doi>
+      <video href="2022.emnlp-industry.46.mp4"/>
     </paper>
     <paper id="47">
       <title>Prototype-Representations for Training Data Filtering in Weakly-Supervised Information Extraction</title>
@@ -12377,6 +12828,7 @@
       <url hash="be932c34">2022.emnlp-industry.48</url>
       <bibkey>hao-etal-2022-cgf</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.48</doi>
+      <video href="2022.emnlp-industry.48.mp4"/>
     </paper>
     <paper id="49">
       <title>Entity-level Sentiment Analysis in Contact Center Telephone Conversations</title>
@@ -12391,6 +12843,7 @@
       <url hash="32ce28b8">2022.emnlp-industry.49</url>
       <bibkey>fu-etal-2022-entity</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.49</doi>
+      <video href="2022.emnlp-industry.49.mp4"/>
     </paper>
     <paper id="50">
       <title><fixed-case>QUILL</fixed-case>: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation</title>
@@ -12405,6 +12858,7 @@
       <url hash="c2a6f0ce">2022.emnlp-industry.50</url>
       <bibkey>srinivasan-etal-2022-quill</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.50</doi>
+      <video href="2022.emnlp-industry.50.mp4"/>
     </paper>
     <paper id="51">
       <title>Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants</title>
@@ -12418,6 +12872,7 @@
       <url hash="3404460f">2022.emnlp-industry.51</url>
       <bibkey>qian-etal-2022-distinguish</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.51</doi>
+      <video href="2022.emnlp-industry.51.mp4"/>
     </paper>
     <paper id="52">
       <title><fixed-case>PLATO</fixed-case>-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt Learning</title>
@@ -12435,6 +12890,7 @@
       <url hash="ddd90b71">2022.emnlp-industry.52</url>
       <bibkey>lei-etal-2022-plato</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.52</doi>
+      <video href="2022.emnlp-industry.52.mp4"/>
     </paper>
     <paper id="53">
       <title>Dense Feature Memory Augmented Transformers for <fixed-case>COVID</fixed-case>-19 Vaccination Search Classification</title>
@@ -12451,6 +12907,7 @@
       <url hash="d1c5d696">2022.emnlp-industry.53</url>
       <bibkey>gupta-etal-2022-dense</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.53</doi>
+      <video href="2022.emnlp-industry.53.mp4"/>
     </paper>
     <paper id="54">
       <title>Full-Stack Information Extraction System for Cybersecurity Intelligence</title>
@@ -12461,6 +12918,7 @@
       <url hash="56ec8349">2022.emnlp-industry.54</url>
       <bibkey>park-lee-2022-full</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.54</doi>
+      <video href="2022.emnlp-industry.54.mp4"/>
     </paper>
     <paper id="55">
       <title>Deploying Unified <fixed-case>BERT</fixed-case> Moderation Model for <fixed-case>E</fixed-case>-Commerce Reviews</title>
@@ -12471,6 +12929,7 @@
       <url hash="f2d72a07">2022.emnlp-industry.55</url>
       <bibkey>nayak-garera-2022-deploying</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.55</doi>
+      <video href="2022.emnlp-industry.55.mp4"/>
     </paper>
     <paper id="56">
       <title><fixed-case>S</fixed-case>im<fixed-case>ANS</fixed-case>: Simple Ambiguous Negatives Sampling for Dense Text Retrieval</title>
@@ -12489,6 +12948,7 @@
       <bibkey>zhou-etal-2022-simans</bibkey>
       <abstract>Sampling proper negatives from a large document pool is vital to effectively train a dense retrieval model. However, existing negative sampling strategies suffer from the uninformative or false negative problem. In this work, we empirically show that according to the measured relevance scores, the negatives ranked around the positives are generally more informative and less likely to be false negatives. Intuitively, these negatives are not too hard (<i>may be false negatives</i>) or too easy (<i>uninformative</i>). They are the ambiguous negatives and need more attention during training.Thus, we propose a simple ambiguous negatives sampling method, SimANS, which incorporates a new sampling probability distribution to sample more ambiguous negatives.Extensive experiments on four public and one industry datasets show the effectiveness of our approach.We made the code and models publicly available in <url>https://github.com/microsoft/SimXNS</url>.</abstract>
       <doi>10.18653/v1/2022.emnlp-industry.56</doi>
+      <video href="2022.emnlp-industry.56.mp4"/>
     </paper>
     <paper id="57">
       <title>Revisiting and Advancing <fixed-case>C</fixed-case>hinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training</title>
@@ -12506,6 +12966,7 @@
       <url hash="7d51f1ec">2022.emnlp-industry.57</url>
       <bibkey>zhang-etal-2022-revisiting</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.57</doi>
+      <video href="2022.emnlp-industry.57.mp4"/>
     </paper>
     <paper id="58">
       <title>A Stacking-based Efficient Method for Toxic Language Detection on Live Streaming Chat</title>
@@ -12517,6 +12978,7 @@
       <url hash="15dce59e">2022.emnlp-industry.58</url>
       <bibkey>oikawa-etal-2022-stacking</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.58</doi>
+      <video href="2022.emnlp-industry.58.mp4"/>
     </paper>
     <paper id="59">
       <title>End-to-End Speech to Intent Prediction to improve <fixed-case>E</fixed-case>-commerce Customer Support Voicebot in <fixed-case>H</fixed-case>indi and <fixed-case>E</fixed-case>nglish</title>
@@ -12528,6 +12990,7 @@
       <url hash="4059d922">2022.emnlp-industry.59</url>
       <bibkey>goyal-etal-2022-end</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.59</doi>
+      <video href="2022.emnlp-industry.59.mp4"/>
     </paper>
     <paper id="60">
       <title><fixed-case>PILE</fixed-case>: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation</title>
@@ -12545,6 +13008,7 @@
       <url hash="17deb019">2022.emnlp-industry.60</url>
       <bibkey>cai-etal-2022-pile</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.60</doi>
+      <video href="2022.emnlp-industry.60.mp4"/>
     </paper>
     <paper id="61">
       <title>A Comprehensive Evaluation of Biomedical Entity-centric Search</title>
@@ -12568,6 +13032,7 @@
       <url hash="89ba6b60">2022.emnlp-industry.62</url>
       <bibkey>morishita-etal-2022-domain</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.62</doi>
+      <video href="2022.emnlp-industry.62.mp4"/>
     </paper>
     <paper id="63">
       <title>Biomedical <fixed-case>NER</fixed-case> for the Enterprise with Distillated <fixed-case>BERN</fixed-case>2 and the Kazu Framework</title>
@@ -12581,6 +13046,7 @@
       <url hash="2d7c9636">2022.emnlp-industry.63</url>
       <bibkey>yoon-etal-2022-biomedical</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.63</doi>
+      <video href="2022.emnlp-industry.63.mp4"/>
     </paper>
     <paper id="64">
       <title>Large-scale Machine Translation for <fixed-case>I</fixed-case>ndian Languages in <fixed-case>E</fixed-case>-commerce under Low Resource Constraints</title>
@@ -12591,6 +13057,7 @@
       <url hash="50f9d95b">2022.emnlp-industry.64</url>
       <bibkey>patil-garera-2022-large</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.64</doi>
+      <video href="2022.emnlp-industry.64.mp4"/>
     </paper>
     <paper id="65">
       <title>Topic Modeling by Clustering Language Model Embeddings: Human Validation on an Industry Dataset</title>
@@ -12601,6 +13068,7 @@
       <url hash="54c3a16f">2022.emnlp-industry.65</url>
       <bibkey>eklund-forsman-2022-topic</bibkey>
       <doi>10.18653/v1/2022.emnlp-industry.65</doi>
+      <video href="2022.emnlp-industry.65.mp4"/>
     </paper>
   </volume>
   <event id="emnlp-2022">
@@ -12609,6 +13077,71 @@
       <location>Abu Dhabi</location>
       <dates>December 7–11, 2022</dates>
     </meta>
+    <links>
+      <url type="website">https://2022.emnlp.org</url>
+      <url type="handbook">2022.emnlp.handbook.pdf</url>
+    </links>
+    <talk>
+      <title>Keynote 1: The multimodal language faculty and the visual languages of comics</title>
+      <speaker><first>Neil</first><last>Cohn</last></speaker>
+      <url type="video">2022.emnlp.keynote1.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 2: Towards a Foundation for <fixed-case>AGI</fixed-case></title>
+      <speaker><first>Gary</first><last>Marcus</last></speaker>
+      <url type="video">2022.emnlp.keynote2.mp4</url>
+    </talk>
+    <talk>
+      <title>Industry Track Keynote: Takeaways from a systematic study of 75<fixed-case>K</fixed-case> models on <fixed-case>H</fixed-case>ugging <fixed-case>F</fixed-case>ace</title>
+      <speaker><first>Nazneen</first><last>Rajani</last></speaker>
+      <url type="video">2022.emnlp.keynote-industry.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session</title>
+      <speaker><first>Noah A.</first><last>Smith</last></speaker>
+      <speaker><first>Yoav</first><last>Goldberg</last></speaker>
+      <speaker><first>Nizar</first><last>Habash</last></speaker>
+      <url type="video">2022.emnlp.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting</title>
+      <speaker><first>Hang</first><last>Li</last></speaker>
+      <speaker><first>Mona</first><last>Diab</last></speaker>
+      <speaker><first>Sien</first><last>Moens</last></speaker>
+      <speaker><first>Noah A.</first><last>Smith</last></speaker>
+      <speaker><first>Alice</first><last>Oh</last></speaker>
+      <speaker><first>Monojit</first><last>Choudhury</last></speaker>
+      <speaker><first>Nizar</first><last>Habash</last></speaker>
+      <url type="video">2022.emnlp.business-meeting.mp4</url>
+    </talk>
+    <talk>
+      <title>Panel: Careers in <fixed-case>NLP</fixed-case></title>
+      <speaker><first>Bing</first><last>Xiang</last></speaker>
+      <speaker><first>Hatem</first><last>Haddad</last></speaker>
+      <speaker><first>Asli</first><last>Celikyilmaz</last></speaker>
+      <speaker><first>Yunyao</first><last>Li</last></speaker>
+      <url type="video">2022.emnlp.panel1.mp4</url>
+    </talk>
+    <talk>
+      <title>Panel: Conference Theme and Beyond</title>
+      <speaker><first>Dipanjan</first><last>Das</last></speaker>
+      <speaker><first>Marie-Catherine</first><last>de Marneffe</last></speaker>
+      <speaker><first/><last>Mausam</last></speaker>
+      <speaker><first>Yulia</first><last>Tsvetkov</last></speaker>
+      <speaker><first>Andreas</first><last>Vlachos</last></speaker>
+      <speaker><first>Noah A.</first><last>Smith</last></speaker>
+      <url type="video">2022.emnlp.panel2.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session and Closing Session</title>
+      <speaker><first>Noah A.</first><last>Smith</last></speaker>
+      <speaker><first>Yoav</first><last>Goldberg</last></speaker>
+      <speaker><first>Alessandro</first><last>Moschitti</last></speaker>
+      <speaker><first>Yang</first><last>Liu</last></speaker>
+      <speaker><first>Tim</first><last>Baldwin</last></speaker>
+      <speaker><first>Nizar</first><last>Habash</last></speaker>
+      <url type="video">2022.emnlp.closing-session.mp4</url>
+    </talk>
     <colocated>
       <volume-id>2022.findings-emnlp</volume-id>
       <volume-id>2022.conll-1</volume-id>
diff --git a/data/xml/2022.findings.xml b/data/xml/2022.findings.xml
index f4877e595e..e2bb697b6b 100644
--- a/data/xml/2022.findings.xml
+++ b/data/xml/2022.findings.xml
@@ -2407,6 +2407,7 @@
       <bibkey>dugan-etal-2022-feasibility</bibkey>
       <doi>10.18653/v1/2022.findings-acl.151</doi>
       <pwccode url="https://github.com/liamdugan/summary-qg" additional="false">liamdugan/summary-qg</pwccode>
+      <video href="2022.findings-acl.151"/>
     </paper>
     <paper id="152">
       <title>Relevant <fixed-case>C</fixed-case>ommon<fixed-case>S</fixed-case>ense Subgraphs for “What if...” Procedural Reasoning</title>
@@ -2716,6 +2717,7 @@
       <url hash="cc2febb1">2022.findings-acl.171</url>
       <bibkey>ponomareva-etal-2022-training</bibkey>
       <doi>10.18653/v1/2022.findings-acl.171</doi>
+      <video href="2022.findings-acl.171"/>
     </paper>
     <paper id="172">
       <title>Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers</title>
@@ -3360,6 +3362,7 @@
       <pwcdataset url="https://paperswithcode.com/dataset/natural-questions">Natural Questions</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/snli">SNLI</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/svhn">SVHN</pwcdataset>
+      <video href="2022.findings-acl.213.mp4"/>
     </paper>
     <paper id="214">
       <title><fixed-case>ASSIST</fixed-case>: Towards Label Noise-Robust Dialogue State Tracking</title>
@@ -9954,6 +9957,7 @@
       <url hash="8af408ed">2022.findings-emnlp.54</url>
       <bibkey>le-scao-etal-2022-language</bibkey>
       <doi>10.18653/v1/2022.findings-emnlp.54</doi>
+      <video href="2022.findings-emnlp.54.mp4"/>
     </paper>
     <paper id="55">
       <title>Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble</title>
@@ -16567,6 +16571,7 @@ Faster and Smaller Speech Translation without Quality Compromise</title>
       <abstract>The shift of public debate to the digital sphere has been accompanied by a rise in online hate speech. While many promising approaches for hate speech classification have been proposed, studies often focus only on a single language, usually English, and do not address three key concerns: post-deployment performance, classifier maintenance and infrastructural limitations. In this paper, we introduce a new human-in-the-loop BERT-based hate speech classification pipeline and trace its development from initial data collection and annotation all the way to post-deployment. Our classifier, trained using data from our original corpus of over 422k examples, is specifically developed for the inherently multilingual setting of Switzerland and outperforms with its F1 score of 80.5 the currently best-performing BERT-based multilingual classifier by 5.8 F1 points in German and 3.6 F1 points in French. Our systematic evaluations over a 12-month period further highlight the vital importance of continuous, human-in-the-loop classifier maintenance to ensure robust hate speech classification post-deployment.</abstract>
       <url hash="67a2d798">2022.findings-emnlp.548</url>
       <bibkey>kotarcic-etal-2022-human</bibkey>
+      <video href="2022.findings-emnlp.548.mp4"/>
     </paper>
   </volume>
 </collection>
diff --git a/data/xml/2022.naacl.xml b/data/xml/2022.naacl.xml
index 4d004f2cc2..543bfe077b 100644
--- a/data/xml/2022.naacl.xml
+++ b/data/xml/2022.naacl.xml
@@ -7981,6 +7981,7 @@
       <url hash="4d9cc505">2022.naacl-tutorials.1</url>
       <bibkey>malmi-etal-2022-text</bibkey>
       <doi>10.18653/v1/2022.naacl-tutorials.1</doi>
+      <video href="2022.naacl-tutorials.1.mp4"/>
     </paper>
     <paper id="2">
       <title>Self-supervised Representation Learning for Speech Processing</title>
@@ -7998,6 +7999,7 @@
       <bibkey>lee-etal-2022-self</bibkey>
       <doi>10.18653/v1/2022.naacl-tutorials.2</doi>
       <pwccode url="https://github.com/s3prl/s3prl" additional="false">s3prl/s3prl</pwccode>
+      <video href="2022.naacl-tutorials.2.mp4"/>
     </paper>
     <paper id="3">
       <title>New Frontiers of Information Extraction</title>
@@ -8013,6 +8015,7 @@
       <bibkey>chen-etal-2022-new</bibkey>
       <doi>10.18653/v1/2022.naacl-tutorials.3</doi>
       <pwcdataset url="https://paperswithcode.com/dataset/conll">CoNLL++</pwcdataset>
+      <video href="2022.naacl-tutorials.3.mp4"/>
     </paper>
     <paper id="4">
       <title>Human-Centered Evaluation of Explanations</title>
@@ -8028,6 +8031,7 @@
       <url hash="65505c52">2022.naacl-tutorials.4</url>
       <bibkey>boyd-graber-etal-2022-human</bibkey>
       <doi>10.18653/v1/2022.naacl-tutorials.4</doi>
+      <video href="2022.naacl-tutorials.4.mp4"/>
     </paper>
     <paper id="5">
       <title>Tutorial on Multimodal Machine Learning</title>
@@ -8040,6 +8044,13 @@
       <bibkey>morency-etal-2022-tutorial</bibkey>
       <doi>10.18653/v1/2022.naacl-tutorials.5</doi>
       <pwcdataset url="https://paperswithcode.com/dataset/visual-question-answering">Visual Question Answering</pwcdataset>
+      <video href="2022.naacl-tutorials.5.1.mp4"/>
+      <video href="2022.naacl-tutorials.5.2.mp4"/>
+      <video href="2022.naacl-tutorials.5.3.mp4"/>
+      <video href="2022.naacl-tutorials.5.4.mp4"/>
+      <video href="2022.naacl-tutorials.5.5.mp4"/>
+      <video href="2022.naacl-tutorials.5.6.mp4"/>
+      <video href="2022.naacl-tutorials.5.7.mp4"/>
     </paper>
     <paper id="6">
       <title>Contrastive Data and Learning for Natural Language Processing</title>
@@ -8052,6 +8063,7 @@
       <url hash="46b089ea">2022.naacl-tutorials.6</url>
       <bibkey>zhang-etal-2022-contrastive-data</bibkey>
       <doi>10.18653/v1/2022.naacl-tutorials.6</doi>
+      <video href="2022.naacl-tutorials.6.mp4"/>
     </paper>
   </volume>
   <volume id="industry" ingest-date="2022-06-28" type="proceedings">
@@ -8675,6 +8687,61 @@
     </paper>
   </volume>
   <event id="naacl-2022">
+    <meta>
+      <title>2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics</title>
+      <location>Seattle, Washington</location>
+      <dates>July 10-15, 2022</dates>
+    </meta>
+    <links>
+      <url type="website">https://2022.naacl.org</url>
+      <url type="handbook">2022.naacl.handbook.pdf</url>
+    </links>
+    <talk>
+      <title>Keynote 1: Shaping Technology with Moral Imagination: Leveraging the Machinery of Value Sensitive Design</title>
+      <speaker><first>Batya</first><last>Friedman</last></speaker>
+      <url type="video">2022.naacl.keynote1.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 2: <fixed-case>NLP</fixed-case> in <fixed-case>M</fixed-case>exican <fixed-case>S</fixed-case>panish: One of many stories</title>
+      <speaker><first>Manuel</first><last>Montes-y-Gómez</last></speaker>
+      <url type="video">2022.naacl.keynote2.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session</title>
+      <speaker><first>Dan</first><last>Roth</last></speaker>
+      <speaker><first>Marine</first><last>Carpuat</last></speaker>
+      <speaker><first>Ivan</first><last>Meza-Ruiz</last></speaker>
+      <speaker><first>Marie-Catherine</first><last>de Marneffe</last></speaker>
+      <url type="video">2022.naacl.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting: Diversity and Inclusion Financial Accessibility Report</title>
+      <speaker><first>Nedjma</first><last>Ousidhoum</last></speaker>
+      <url type="video">2022.naacl.business-meeting.mp4</url>
+    </talk>
+    <talk>
+      <title>Panel: The Place of Linguistics and Symbolic Structures</title>
+      <speaker><first>Emily M.</first><last>Bender</last></speaker>
+      <speaker><first>Dilek</first><last>Hakkani-Tür</last></speaker>
+      <speaker><first>Chitta</first><last>Baral</last></speaker>
+      <speaker><first>Christopher</first><last>Manning</last></speaker>
+      <speaker><first>Dan</first><last>Roth</last></speaker>
+      <url type="video">2022.naacl.panel.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session</title>
+      <speaker><first>Marie-Catherine</first><last>de Marneffe</last></speaker>
+      <url type="video">2022.naacl.best-papers.mp4</url>
+    </talk>
+    <talk>
+      <title>Closing Session</title>
+      <speaker><first>Dan</first><last>Roth</last></speaker>
+      <speaker><first>Chitta</first><last>Baral</last></speaker>
+      <speaker><first>Emily M.</first><last>Bender</last></speaker>
+      <speaker><first>Dilek</first><last>Hakkani-Tür</last></speaker>
+      <speaker><first>Christopher</first><last>Manning</last></speaker>
+      <url type="video">2022.naacl.closing-session.mp4</url>
+    </talk>
     <colocated>
       <volume-id>2022.findings-naacl</volume-id>
       <volume-id>2022.autosimtrans-1</volume-id>
diff --git a/data/xml/2022.semeval.xml b/data/xml/2022.semeval.xml
index 60783b1363..319e67e9dd 100644
--- a/data/xml/2022.semeval.xml
+++ b/data/xml/2022.semeval.xml
@@ -1113,6 +1113,7 @@
       <doi>10.18653/v1/2022.semeval-1.87</doi>
       <pwcdataset url="https://paperswithcode.com/dataset/hateful-memes">Hateful Memes</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/hateful-memes-challenge">Hateful Memes Challenge</pwcdataset>
+      <video href="2022.semeval-1.87.mp4"/>
     </paper>
     <paper id="88">
       <title><fixed-case>T</fixed-case>eam<fixed-case>O</fixed-case>tter at <fixed-case>S</fixed-case>em<fixed-case>E</fixed-case>val-2022 Task 5: Detecting Misogynistic Content in Multimodal Memes</title>
@@ -1984,6 +1985,7 @@
       <url hash="0a96f31c">2022.semeval-1.155</url>
       <bibkey>chen-etal-2022-semeval</bibkey>
       <doi>10.18653/v1/2022.semeval-1.155</doi>
+      <video href="2022.semeval-1.155.mp4"/>
     </paper>
     <paper id="156">
       <title><fixed-case>EMBEDDIA</fixed-case> at <fixed-case>S</fixed-case>em<fixed-case>E</fixed-case>val-2022 Task 8: Investigating Sentence, Image, and Knowledge Graph Representations for Multilingual News Article Similarity</title>
diff --git a/data/xml/2022.tacl.xml b/data/xml/2022.tacl.xml
index a7ea87a051..12b0b5382f 100644
--- a/data/xml/2022.tacl.xml
+++ b/data/xml/2022.tacl.xml
@@ -321,6 +321,7 @@
       <pages>307–324</pages>
       <url hash="5bcc954f">2022.tacl-1.18</url>
       <bibkey>raifer-etal-2022-designing</bibkey>
+      <video href="2022.tacl-1.18.mp4"/>
     </paper>
     <paper id="19">
       <title>Towards General Natural Language Understanding with Probabilistic Worldbuilding</title>
@@ -455,6 +456,7 @@
       <pages>484–502</pages>
       <url hash="405881b7">2022.tacl-1.28</url>
       <bibkey>sarwar-etal-2022-neighborhood</bibkey>
+      <video href="2022.tacl-1.28.mp4"/>
     </paper>
     <paper id="29">
       <title>Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval</title>
@@ -574,6 +576,7 @@
       <pages>639–658</pages>
       <url hash="4a308122">2022.tacl-1.37</url>
       <bibkey>morio-etal-2022-end</bibkey>
+      <video href="2022.tacl-1.37.mp4"/>
     </paper>
     <paper id="38">
       <title>Is My Model Using the Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning</title>
@@ -1079,6 +1082,7 @@
       <pages>1341–1356</pages>
       <url hash="5da10618">2022.tacl-1.77</url>
       <bibkey>lachmy-etal-2022-draw</bibkey>
+      <video href="2022.tacl-1.77.mp4"/>
     </paper>
     <paper id="78">
       <title>Investigating Reasons for Disagreement in Natural Language Inference</title>
@@ -1089,6 +1093,7 @@
       <pages>1357–1374</pages>
       <url hash="99c5b524">2022.tacl-1.78</url>
       <bibkey>jiang-marneffe-2022-investigating</bibkey>
+      <video href="2022.tacl-1.78.mp4"/>
     </paper>
     <paper id="79">
       <title>The Emergence of Argument Structure in Artificial Languages</title>
@@ -1125,6 +1130,7 @@
       <pages>1423–1439</pages>
       <url hash="c5467521">2022.tacl-1.81</url>
       <bibkey>sartran-etal-2022-transformer</bibkey>
+      <video href="2022.tacl-1.81.mp4"/>
     </paper>
     <paper id="82">
       <title>Explainable Abuse Detection as Intent Classification and Slot Filling</title>
@@ -1146,6 +1152,7 @@
       <pages>1455–1472</pages>
       <url hash="e5c88236">2022.tacl-1.83</url>
       <bibkey>goldman-tsarfaty-2022-morphology</bibkey>
+      <video href="2022.tacl-1.83.mp4"/>
     </paper>
     <paper id="84">
       <title><fixed-case>F</fixed-case>aith<fixed-case>D</fixed-case>ial: A Faithful Benchmark for Information-Seeking Dialogue</title>
diff --git a/data/xml/2023.acl.xml b/data/xml/2023.acl.xml
index bd34dc77aa..03ad180cb3 100644
--- a/data/xml/2023.acl.xml
+++ b/data/xml/2023.acl.xml
@@ -17840,6 +17840,97 @@
     </paper>
   </volume>
   <event id="acl-2023">
+    <meta>
+      <title>61st Annual Meeting of the Association for Computational Linguistics</title>
+      <location>Toronto, Canada</location>
+      <dates>July 9-14, 2023</dates>
+    </meta>
+    <links>
+      <url type="website">https://2023.aclweb.org</url>
+      <url type="handbook">2023.acl.handbook.pdf</url>
+    </links>
+    <talk>
+      <title>Keynote 1: Two Paths to Intelligence</title>
+      <speaker><first>Geoffrey</first><last>Hinton</last></speaker>
+      <url type="video">2023.acl.keynote1.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 2: Large Language Models as Cultural Technologies: Imitation and Innovation in Children and Models</title>
+      <speaker><first>Alison</first><last>Gopnik</last></speaker>
+      <url type="video">2023.acl.keynote2.mp4</url>
+    </talk>
+    <talk>
+      <title>Lifetime Achievement Award: My Big, Fat 50 Year Journey</title>
+      <speaker><first>Martha</first><last>Palmer</last></speaker>
+      <url type="video">2023.acl.keynote3.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session and Presidential Address</title>
+      <speaker><first>Yang</first><last>Liu</last></speaker>
+      <speaker><first>Naoaki</first><last>Okazaki</last></speaker>
+      <speaker><first>Anna</first><last>Rogers</last></speaker>
+      <speaker><first>Jordan</first><last>Boyd-Graber</last></speaker>
+      <speaker><first>Iryna</first><last>Gurevych</last></speaker>
+      <url type="video">2023.acl.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting</title>
+      <speaker><first>Iryna</first><last>Gurevych</last></speaker>
+      <speaker><first>David</first><last>Yarowski</last></speaker>
+      <speaker><first>Emily M.</first><last>Bender</last></speaker>
+      <url type="video">2023.acl.business-meeting.mp4</url>
+    </talk>
+    <talk>
+      <title><fixed-case>ARR</fixed-case> Info Session</title>
+      <speaker><first/><last>Mausam</last></speaker>
+      <url type="video">2023.acl.arr-info-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Memorial for <fixed-case>D</fixed-case>ragomir <fixed-case>R</fixed-case>adev</title>
+      <speaker><first>Kathy</first><last>McKeown</last></speaker>
+      <speaker><first>Smaranda</first><last>Muresan</last></speaker>
+      <speaker><first>Rada</first><last>Mihalcea</last></speaker>
+      <speaker><first>Lori</first><last>Levin</last></speaker>
+      <speaker><first>Cathy</first><last>Finegan-Dollak</last></speaker>
+      <speaker><first>Alexander</first><last>Fabbri</last></speaker>
+      <url type="video">2023.acl.memorial-dragomir-radev.mp4</url>
+    </talk>
+    <talk>
+      <title>Panel: <fixed-case>L</fixed-case>arge <fixed-case>L</fixed-case>anguage <fixed-case>M</fixed-case>odels</title>
+      <speaker><first>Dan</first><last>Klein</last></speaker>
+      <speaker><first>Margaret</first><last>Mitchell</last></speaker>
+      <speaker><first>Roy</first><last>Schwartz</last></speaker>
+      <speaker><first>Diyi</first><last>Yang</last></speaker>
+      <speaker><first>Iryna</first><last>Gurevych</last></speaker>
+      <url type="video">2023.acl.panel.mp4</url>
+    </talk>
+    <talk>
+      <title>Lifetime Achievement Award Session</title>
+      <speaker><first>Iryna</first><last>Gurevych</last></speaker>
+      <speaker><first>Joakim</first><last>Nivre</last></speaker>
+      <speaker><first>Yusuke</first><last>Miyao</last></speaker>
+      <speaker><first>Christopher</first><last>Manning</last></speaker>
+      <speaker><first>Richard</first><last>Socher</last></speaker>
+      <speaker><first>Irene</first><last>Langkilde</last></speaker>
+      <speaker><first>Hinrich</first><last>Schütze</last></speaker>
+      <url type="video">2023.acl.lifetime-achievement-award.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session</title>
+      <speaker><first>Anna</first><last>Rogers</last></speaker>
+      <url type="video">2023.acl.best-papers.mp4</url>
+    </talk>
+    <talk>
+      <title>Closing Session</title>
+      <speaker><first>Yang</first><last>Liu</last></speaker>
+      <speaker><first>Jong</first><last>Park</last></speaker>
+      <speaker><first>Boxing</first><last>Chen</last></speaker>
+      <speaker><first>Michael</first><last>Strube</last></speaker>
+      <speaker><first>Naoki</first><last>Okazaki</last></speaker>
+      <speaker><first>Kevin</first><last>Duh</last></speaker>
+      <speaker><first>Claire</first><last>Gardent</last></speaker>
+      <url type="video">2023.acl.closing-session.mp4</url>
+    </talk>
     <colocated>
       <volume-id>2023.findings-acl</volume-id>
       <volume-id>2023.americasnlp-1</volume-id>
diff --git a/data/xml/2023.cl.xml b/data/xml/2023.cl.xml
index 820954d873..0ff603cb3a 100644
--- a/data/xml/2023.cl.xml
+++ b/data/xml/2023.cl.xml
@@ -21,6 +21,7 @@
       <pages>1–72</pages>
       <url hash="da520382">2023.cl-1.1</url>
       <bibkey>troiano-etal-2023-dimensional</bibkey>
+      <video href="2023.cl-1.1.mp4"/>
     </paper>
     <paper id="2">
       <title>Transformers and the Representation of Biomedical Background Knowledge</title>
@@ -36,6 +37,7 @@
       <pages>73–115</pages>
       <url hash="0e303b6f">2023.cl-1.2</url>
       <bibkey>wysocki-etal-2023-transformers</bibkey>
+      <video href="2023.cl-1.2.mp4"/>
     </paper>
     <paper id="3">
       <title>It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers</title>
@@ -46,6 +48,7 @@
       <pages>117–156</pages>
       <url hash="b5c72bb0">2023.cl-1.3</url>
       <bibkey>tang-surdeanu-2023-takes</bibkey>
+      <video href="2023.cl-1.3.mp4"/>
     </paper>
     <paper id="4">
       <title>Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future</title>
@@ -57,6 +60,7 @@
       <pages>157–198</pages>
       <url hash="491b37f9">2023.cl-1.4</url>
       <bibkey>klie-etal-2023-annotation</bibkey>
+      <video href="2023.cl-1.4.mp4"/>
     </paper>
     <paper id="5">
       <title>Curing the <fixed-case>SICK</fixed-case> and Other <fixed-case>NLI</fixed-case> Maladies</title>
@@ -340,6 +344,7 @@
       <pages>777–840</pages>
       <url hash="1e5b02fe">2023.cl-4.2</url>
       <bibkey>rashkin-etal-2023-measuring</bibkey>
+      <video href="2023.cl-4.2.mp4"/>
     </paper>
     <paper id="3">
       <title>Generation and Polynomial Parsing of Graph Languages with Non-Structural Reentrancies</title>
@@ -351,6 +356,7 @@
       <pages>841–882</pages>
       <url hash="338b8904">2023.cl-4.3</url>
       <bibkey>bjorklund-etal-2023-generation</bibkey>
+      <video href="2023.cl-4.3.mp4"/>
     </paper>
     <paper id="4">
       <title>Capturing Fine-Grained Regional Differences in Language Use through Voting Precinct Embeddings</title>
@@ -361,6 +367,7 @@
       <pages>883–942</pages>
       <url hash="c3788553">2023.cl-4.4</url>
       <bibkey>rosenfeld-hinrichs-2023-capturing</bibkey>
+      <video href="2023.cl-4.4.mp4"/>
     </paper>
     <paper id="5">
       <title>Languages Through the Looking Glass of <fixed-case>BPE</fixed-case> Compression</title>
@@ -372,6 +379,7 @@
       <pages>943–1001</pages>
       <url hash="df47a4b1">2023.cl-4.5</url>
       <bibkey>gutierrez-vasques-etal-2023-languages</bibkey>
+      <video href="2023.cl-4.5.mp4"/>
     </paper>
     <paper id="6">
       <title>Language Embeddings Sometimes Contain Typological Generalizations</title>
@@ -382,6 +390,7 @@
       <pages>1003–1051</pages>
       <url hash="5a7ee79d">2023.cl-4.6</url>
       <bibkey>ostling-kurfali-2023-language</bibkey>
+      <video href="2023.cl-4.6.mp4"/>
     </paper>
   </volume>
 </collection>
diff --git a/data/xml/2023.eacl.xml b/data/xml/2023.eacl.xml
index ef68a7341f..f555bcac6f 100644
--- a/data/xml/2023.eacl.xml
+++ b/data/xml/2023.eacl.xml
@@ -4487,6 +4487,8 @@
       <abstract>With NLP research now quickly being transferred into real-world applications, it is important to be aware of and think through the consequences of our scientific investigation. Such ethical considerations are important in both authoring and reviewing. This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues and review common considerations that recur in NLP research. The methodology is interactive and participatory, including case studies and working in groups. Importantly, the participants will be co-building the tutorial outcomes and will be working to create further tutorial materials to share as public outcomes.</abstract>
       <url hash="90ab3e4e">2023.eacl-tutorials.4</url>
       <bibkey>benotti-etal-2023-understanding</bibkey>
+      <video href="2023.eacl-tutorials.4.1.mp4"/>
+      <video href="2023.eacl-tutorials.4.2.mp4"/>
       <doi>10.18653/v1/2023.eacl-tutorials.4</doi>
     </paper>
     <paper id="5">
@@ -4525,6 +4527,56 @@
       <url type="website">https://2023.eacl.org</url>
       <url type="handbook">2023.eacl.handbook.pdf</url>
     </links>
+    <talk>
+      <title>Keynote 1: Going beyond the benefits of scale by reasoning about data</title>
+      <speaker><first>Edward</first><last>Grefenstette</last></speaker>
+      <url type="video">2023.eacl.keynote1.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 2: Chatbots for Good and Evil</title>
+      <speaker><first>Kevin</first><last>Munger</last></speaker>
+      <url type="video">2023.eacl.keynote2.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 3: Language Use in Embodied AI</title>
+      <speaker><first>Joyce</first><last>Chai</last></speaker>
+      <url type="video">2023.eacl.keynote3.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session</title>
+      <speaker><first>Alessandro</first><last>Moschitti</last></speaker>
+      <speaker><first>Isabelle</first><last>Augenstein</last></speaker>
+      <speaker><first>Andreas</first><last>Vlachos</last></speaker>
+      <speaker><first>Kathleen</first><last>McKeown</last></speaker>
+      <speaker><first>Roberto</first><last>Basili</last></speaker>
+      <speaker><first>Marko</first><last>Tadić</last></speaker>
+      <url type="video">2023.eacl.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting</title>
+      <speaker><first>Preslav</first><last>Nakov</last></speaker>
+      <speaker><first>Jochen L.</first><last>Leidner</last></speaker>
+      <speaker><first>Haiming</first><last>Liu</last></speaker>
+      <speaker><first>Andreas</first><last>Vlachos</last></speaker>
+      <speaker><first>Isabelle</first><last>Augenstein</last></speaker>
+      <url type="video">2023.eacl.business-meeting.mp4</url>
+    </talk>
+    <talk>
+      <title>Panel: Low-resource Languages in <fixed-case>NLP</fixed-case> Products</title>
+      <speaker><first>Viktoria</first><last>Kolomiets</last></speaker>
+      <speaker><first>Mariana</first><last>Romanyshyn</last></speaker>
+      <speaker><first>Oleksii</first><last>Molchanovskyi</last></speaker>
+      <speaker><first>Oles</first><last>Dobosevych</last></speaker>
+      <speaker><first>Mariana</first><last>Romanyshyn</last></speaker>
+      <url type="video">2023.eacl.panel.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session and Closing Session</title>
+      <speaker><first>Alessandro</first><last>Moschitti</last></speaker>
+      <speaker><first>Isabelle</first><last>Augenstein</last></speaker>
+      <speaker><first>Andreas</first><last>Vlachos</last></speaker>
+      <url type="video">2023.eacl.closing-session.mp4</url>
+    </talk>
     <colocated>
       <volume-id>2023.findings-eacl</volume-id>
       <volume-id>2023.bsnlp-1</volume-id>
diff --git a/data/xml/2023.emnlp.xml b/data/xml/2023.emnlp.xml
index f1a51d0ae6..54b991b813 100644
--- a/data/xml/2023.emnlp.xml
+++ b/data/xml/2023.emnlp.xml
@@ -7707,6 +7707,7 @@
       <url hash="ab734b64">2023.emnlp-main.550</url>
       <bibkey>cao-etal-2023-unnatural</bibkey>
       <doi>10.18653/v1/2023.emnlp-main.550</doi>
+      <video href="2023.emnlp-main.550.mp4"/>
     </paper>
     <paper id="551">
       <title>Detecting and Mitigating Hallucinations in Multilingual Summarisation</title>
@@ -15444,6 +15445,7 @@
       <url hash="28e65a26">2023.emnlp-demo.44</url>
       <bibkey>zhang-etal-2023-zhujiu</bibkey>
       <doi>10.18653/v1/2023.emnlp-demo.44</doi>
+      <video href="2023.emnlp-demo.44.mp4"/>
     </paper>
     <paper id="45">
       <title><fixed-case>P</fixed-case>aper<fixed-case>M</fixed-case>age: A Unified Toolkit for Processing, Representing, and Manipulating Visually-Rich Scientific Documents</title>
@@ -16716,6 +16718,59 @@
       <location>Singapore</location>
       <dates>December 6–10, 2023</dates>
     </meta>
+    <links>
+      <url type="website">https://2023.emnlp.org</url>
+      <url type="handbook">2023.emnlp.handbook.pdf</url>
+    </links>
+    <talk>
+      <title>Keynote 1: Human-Centric Natural Language Processing</title>
+      <speaker><first>Jong</first><last>Park</last></speaker>
+      <url type="video">2023.emnlp.keynote1.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 2: From Speech to Emotion to Mood: Mental Health Modeling in Real-World Environments.</title>
+      <speaker><first>Emily Mower</first><last>Provost</last></speaker>
+      <url type="video">2023.emnlp.keynote2.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 3: Academic <fixed-case>NLP</fixed-case> research in the Age of <fixed-case>LLM</fixed-case>s: Nothing but blue skies!</title>
+      <speaker><first>Christopher</first><last>Manning</last></speaker>
+      <url type="video">2023.emnlp.keynote3.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session</title>
+      <speaker><first>Yuji</first><last>Matsumoto</last></speaker>
+      <speaker><first>Houda</first><last>Bouamor</last></speaker>
+      <speaker><first>Juan</first><last>Pino</last></speaker>
+      <speaker><first>Kalika</first><last>Bali</last></speaker>
+      <speaker><first>Haizhou</first><last>Li</last></speaker>
+      <url type="video">2023.emnlp.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting</title>
+      <speaker><first>Mona</first><last>Diab</last></speaker>
+      <speaker><first>David</first><last>Yarowsky</last></speaker>
+      <speaker><first>Jennifer</first><last>Rachford</last></speaker>
+      <speaker><first>Isabelle</first><last>Augenstein</last></speaker>
+      <url type="video">2023.emnlp.business-meeting.mp4</url>
+    </talk>
+    <talk>
+      <title>Panel: Beyond Text: Inclusive Human Communication with Language Technology</title>
+      <speaker><first>Lourdes</first><last>de Rioja</last></speaker>
+      <speaker><first>Abraham</first><last>Glasser</last></speaker>
+      <speaker><first>Chengkuo</first><last>Lee</last></speaker>
+      <speaker><first>María Inés</first><last>Torres</last></speaker>
+      <speaker><first>Monojit</first><last>Choudhury</last></speaker>
+      <url type="video">2023.emnlp.panel.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session and Closing Session</title>
+      <speaker><first>Kalika</first><last>Bali</last></speaker>
+      <speaker><first>Michael</first><last>Strube</last></speaker>
+      <speaker><first>Yuji</first><last>Matsumoto</last></speaker>
+      <speaker><first>Jordan</first><last>Boyd-Graber</last></speaker>
+      <url type="video">2023.emnlp.closing-session.mp4</url>
+    </talk>
     <colocated>
       <volume-id>2023.findings-emnlp</volume-id>
       <volume-id>2023.arabicnlp-1</volume-id>
diff --git a/data/xml/2023.gem.xml b/data/xml/2023.gem.xml
index 1a7ac29d58..3188c1bba0 100644
--- a/data/xml/2023.gem.xml
+++ b/data/xml/2023.gem.xml
@@ -116,6 +116,7 @@
       <abstract>In the dynamic field of eCommerce, the quality and comprehensiveness of product descriptions are pivotal for enhancing search visibility and customer engagement. Effective product descriptions can address the ‘cold start’ problem, align with market trends, and ultimately lead to increased click-through rates. Traditional methods for crafting these descriptions often involve significant human effort and may lack both consistency and scalability. This paper introduces a novel methodology for automating product description generation using the LLAMA 2.0 7B language model. We train the model on a dataset of authentic product descriptions from Walmart, one of the largest eCommerce platforms. The model is then fine-tuned for domain-specific language features and eCommerce nuances to enhance its utility in sales and user engagement. We employ multiple evaluation metrics—including NDCG, customer click-through rates, and human assessments—to validate the effectiveness of our approach. Our findings reveal that the system is not only scalable but also significantly reduces the human workload involved in creating product descriptions. This study underscores the considerable potential of large language models like LLAMA 2.0 7B in automating and optimizing various facets of eCommerce platforms, offering significant business impact, including improved search functionality and increased sales.</abstract>
       <url hash="93cd6548">2023.gem-1.8</url>
       <bibkey>zhou-etal-2023-leveraging</bibkey>
+      <video href="2023.gem-1.8.mp4"/>
     </paper>
     <paper id="9">
       <title><fixed-case>QAMPARI</fixed-case>: A Benchmark for Open-domain Questions with Many Answers</title>
@@ -274,6 +275,7 @@
       <abstract>At the staggering pace with which the capabilities of large language models (LLMs) are increasing, creating future-proof evaluation sets to assess their understanding becomes more and more challenging. In this paper, we propose a novel paradigm for evaluating LLMs which leverages the idea that correct world understanding should be consistent across different (Fregean) senses of the same meaning. Accordingly, we measure understanding not in terms of correctness but by evaluating consistency across multiple senses that are generated by the model itself. We showcase our approach by instantiating a test where the different senses are different languages, hence using multilingual self-consistency as a litmus test for the model’s understanding and simultaneously addressing the important topic of multilingualism. Taking one of the latest versions of ChatGPT as our object of study, we evaluate multilingual consistency for two different tasks across three different languages. We show that its multilingual consistency is still lacking, and that its task and world understanding are thus not language-independent. As our approach does not require any static evaluation corpora in languages other than English, it can easily and cheaply be extended to different languages and tasks and could become an integral part of future benchmarking efforts.</abstract>
       <url hash="4538e4ea">2023.gem-1.22</url>
       <bibkey>ohmer-etal-2023-separating</bibkey>
+      <video href="2023.gem-1.22.mp4"/>
     </paper>
     <paper id="23">
       <title>Text Encoders Lack Knowledge: Leveraging Generative <fixed-case>LLM</fixed-case>s for Domain-Specific Semantic Textual Similarity</title>
@@ -286,6 +288,7 @@
       <abstract>Amidst the sharp rise in the evaluation of large language models (LLMs) on various tasks, we find that semantic textual similarity (STS) has been under-explored. In this study, we show that STS can be cast as a text generation problem while maintaining strong performance on multiple STS benchmarks. Additionally, we show generative LLMs significantly outperform existing encoder-based STS models when characterizing the semantic similarity between two texts with complex semantic relationships dependent on world knowledge. We validate this claim by evaluating both generative LLMs and existing encoder-based STS models on three newly-collected STS challenge sets which require world knowledge in the domains of Health, Politics, and Sports. All newly-collected data is sourced from social media content posted after May 2023 to ensure the performance of closed-source models like ChatGPT cannot be credited to memorization. Our results show that, on average, generative LLMs outperform the best encoder-only baselines by an average of 22.3% on STS tasks requiring world knowledge. Our results suggest generative language models with STS-specific prompting strategies achieve state-of-the-art performance in complex, domain-specific STS tasks.</abstract>
       <url hash="3106a585">2023.gem-1.23</url>
       <bibkey>gatto-etal-2023-text</bibkey>
+      <video href="2023.gem-1.23.mp4"/>
     </paper>
     <paper id="24">
       <title>To Burst or Not to Burst: Generating and Quantifying Improbable Text</title>
@@ -327,6 +330,7 @@
       <abstract>Data quality is a problem that perpetually resurfaces throughout the field of NLP, regardless of task, domain, or architecture, and remains especially severe for lower-resource languages. A typical and insidious issue, affecting both training data and model output, is data that is repetitive and dominated by linguistically uninteresting boilerplate, such as price catalogs or computer-generated log files. Though this problem permeates many web-scraped corpora, there has yet to be a benchmark to test against, or a systematic study to find simple metrics that generalize across languages and agree with human judgements of data quality. In the present work, we create and release BREAD, a human-labeled benchmark on repetitive boilerplate vs. plausible linguistic content, spanning 360 languages. We release several baseline CRED (Character REDundancy) scores along with it, and evaluate their effectiveness on BREAD. We hope that the community will use this resource to develop better filtering methods, and that our reference implementations of CRED scores can become standard corpus evaluation tools, driving the development of cleaner language modeling corpora, especially in low-resource languages.</abstract>
       <url hash="58a7da96">2023.gem-1.27</url>
       <bibkey>caswell-etal-2023-separating</bibkey>
+      <video href="2023.gem-1.27.mp4"/>
     </paper>
     <paper id="28">
       <title>Elo Uncovered: Robustness and Best Practices in Language Model Evaluation</title>
@@ -370,6 +374,7 @@
       <abstract>In the rapidly evolving landscape of Large Language Models (LLMs), introduction of well-defined and standardized evaluation methodologies remains a crucial challenge. This paper traces the historical trajectory of LLM evaluations, from the foundational questions posed by Alan Turing to the modern era of AI research. We categorize the evolution of LLMs into distinct periods, each characterized by its unique benchmarks and evaluation criteria. As LLMs increasingly mimic human-like behaviors, traditional evaluation proxies, such as the Turing test, have become less reliable. We emphasize the pressing need for a unified evaluation system, given the broader societal implications of these models. Through an analysis of common evaluation methodologies, we advocate for a qualitative shift in assessment approaches, underscoring the importance of standardization and objective criteria. This work serves as a call for the AI community to collaboratively address the challenges of LLM evaluation, ensuring their reliability, fairness, and societal benefit.</abstract>
       <url hash="43a3904e">2023.gem-1.31</url>
       <bibkey>tikhonov-yamshchikov-2023-post</bibkey>
+      <video href="2023.gem-1.31.mp4"/>
     </paper>
     <paper id="32">
       <title>A Simple yet Efficient Ensemble Approach for <fixed-case>AI</fixed-case>-generated Text Detection</title>
diff --git a/data/xml/2023.insights.xml b/data/xml/2023.insights.xml
index de647bb05f..801c09f2b4 100644
--- a/data/xml/2023.insights.xml
+++ b/data/xml/2023.insights.xml
@@ -221,6 +221,7 @@
       <abstract>We probe structural and discourse aspects of coreferential relationships in a fine-tuned Dutch BERT event coreference model. Previous research has suggested that no such knowledge is encoded in BERT-based models and the classification of coreferential relationships ultimately rests on outward lexical similarity. While we show that BERT can encode a (very) limited number of these discourse aspects (thus disproving assumptions in earlier research), we also note that knowledge of many structural features of coreferential relationships is absent from the encodings generated by the fine-tuned BERT model.</abstract>
       <url hash="f24b1876">2023.insights-1.13</url>
       <bibkey>de-langhe-etal-2023-bert</bibkey>
+      <video href="2023.insights-1.13.mp4"/>
     </paper>
     <paper id="14">
       <title>Estimating Numbers without Regression</title>
@@ -231,6 +232,7 @@
       <abstract>Despite recent successes in language models, their ability to represent numbers is insufficient. Humans conceptualize numbers based on their magnitudes, effectively projecting them on a number line; whereas subword tokenization fails to explicitly capture magnitude by splitting numbers into arbitrary chunks. To alleviate this shortcoming, alternative approaches have been proposed that modify numbers at various stages of the language modeling pipeline. These methods change either the (1) notation in which numbers are written (eg scientific vs decimal), the (2) vocabulary used to represent numbers or the entire (3) architecture of the underlying language model, to directly regress to a desired number. Previous work suggests that architectural change helps achieve state-of-the-art on number estimation but we find an insightful ablation - changing the model”s vocabulary instead (eg introduce a new token for numbers in range 10-100) is a far better trade-off. In the context of masked number prediction, a carefully designed tokenization scheme is both the simplest to implement and sufficient, ie with similar performance to the state-of-the-art approach that requires making significant architectural changes. Finally, we report similar trends on the downstream task of numerical fact estimation (for Fermi Problems) and discuss reasons behind our findings.</abstract>
       <url hash="4bb90ecd">2023.insights-1.14</url>
       <bibkey>thawani-etal-2023-estimating</bibkey>
+      <video href="2023.insights-1.14.mp4"/>
     </paper>
   </volume>
 </collection>
diff --git a/data/xml/2023.latechclfl.xml b/data/xml/2023.latechclfl.xml
index 6798865ba6..a56bcd8cd5 100644
--- a/data/xml/2023.latechclfl.xml
+++ b/data/xml/2023.latechclfl.xml
@@ -106,6 +106,7 @@
       <abstract>The subject of this article is the application of NLP and text-mining methods to the analysis of two large bibliographies: Polish one, based on the catalogs of the National Library in Warsaw, and the other German one, created by Deutsche Nationalbibliothek. The data in both collections are stored in MARC 21 format, allowing the selection of relevant fields that are used for further processing (basically author, title, and date). The volume of the Polish corpus (after filtering out non-relevant or incomplete items) includes 1.4 mln of records, and that of the German corpus 7.5 mln records. The time span of both bibliographies extends from 1801 to 2021. The aim of the study is to compare the gender distribution of book authors in Polish and German databases over more than two centuries. The proportions of male and female authors since 1801 were calculated automatically, and NLP methods such as document vector embedding based on deep BERT networks were used to extract topics from titles. The gender of the Polish authors was recognized based on the morphology of the first names, and that of the German authors based on a predefined list. The study found that the proportion of female authors has been steadily increasing both in Poland and in German countries (currently around 43%). However, the topics of women’s and men’s writings invariably remain different since 1801.</abstract>
       <url hash="e40dcaf2">2023.latechclfl-1.7</url>
       <bibkey>pawlowski-walkowiak-2023-great</bibkey>
+      <video href="2023.latechclfl-1.7.mp4"/>
       <doi>10.18653/v1/2023.latechclfl-1.7</doi>
     </paper>
     <paper id="8">
@@ -157,6 +158,7 @@
       <abstract>Development funds are essential to finance climate change adaptation and are thus an important part of international climate policy. How ever, the absence of a common reporting practice makes it difficult to assess the amount and distribution of such funds. Research has questioned the credibility of reported figures, indicating that adaptation financing is in fact lower than published figures suggest. Projects claiming a greater relevance to climate change adaptation than they target are referred to as “overreported”. To estimate realistic rates of overreporting in large data sets over times, we propose an approach based on state-of-the-art text classification. To date, assessments of credibility have relied on small, manually evaluated samples. We use such a sample data set to train a classifier with an accuracy of 89.81%±0.83% (tenfold cross-validation) and extrapolate to larger data sets to identify overreporting. Additionally, we propose a method that incorporates evidence of smaller, higher-quality data to correct predicted rates using Bayes’ theorem. This enables a comparison of different annotation schemes to estimate the degree of overreporting in climate change adaptation. Our results support findings that indicate extensive overreporting of 32.03% with a credible interval of [19.81%; 48.34%].</abstract>
       <url hash="29714a7d">2023.latechclfl-1.11</url>
       <bibkey>borst-etal-2023-constructing</bibkey>
+      <video href="2023.latechclfl-1.11.mp4"/>
       <doi>10.18653/v1/2023.latechclfl-1.11</doi>
     </paper>
     <paper id="12">
@@ -168,6 +170,7 @@
       <abstract>In this paper, we present approaches for the automated extraction and disambiguation of a part of the stylistic device Vossian Antonomasia (VA), namely the target entity that is described by the expression. We model the problem as a coreference resolution task and a question answering task and also combine both tasks. To tackle these tasks, we utilize state-of-the-art models in these areas. In addition, we visualize the connection between the source and target entities of VA in a web demo to get a deeper understanding of the interaction of entities used in VA expressions.</abstract>
       <url hash="2369309e">2023.latechclfl-1.12</url>
       <bibkey>schwab-etal-2023-madonna</bibkey>
+      <video href="2023.latechclfl-1.12.mp4"/>
       <doi>10.18653/v1/2023.latechclfl-1.12</doi>
     </paper>
     <paper id="13">
diff --git a/data/xml/2023.nlposs.xml b/data/xml/2023.nlposs.xml
index bc20d15adc..02ef7a3e2b 100644
--- a/data/xml/2023.nlposs.xml
+++ b/data/xml/2023.nlposs.xml
@@ -53,6 +53,7 @@
       <url hash="811daf70">2023.nlposs-1.3</url>
       <bibkey>beauchemin-2023-deepparse</bibkey>
       <doi>10.18653/v1/2023.nlposs-1.3</doi>
+      <video href="2023.nlposs-1.3.mp4"/>
     </paper>
     <paper id="4">
       <title><fixed-case>P</fixed-case>y<fixed-case>T</fixed-case>hai<fixed-case>NLP</fixed-case>: <fixed-case>T</fixed-case>hai Natural Language Processing in Python</title>
diff --git a/data/xml/2023.rail.xml b/data/xml/2023.rail.xml
index 3d10068dd5..03e3228f1e 100644
--- a/data/xml/2023.rail.xml
+++ b/data/xml/2023.rail.xml
@@ -66,6 +66,7 @@
       <abstract>This paper describes the SpeechReporting database, an online collection of corpora annotated for a range of discourse phenomena. The corpora contain folktales from 7 lesser-studied West African languages. Apart from its value for theoretical linguistics, especially for the study of reported speech, the database is an important resource for the preservation of intangible cultural heritage of minority languages and the development and testing of cross-linguistically applicable computational tools.</abstract>
       <url hash="280c619d">2023.rail-1.4</url>
       <bibkey>aplonova-etal-2023-speechreporting</bibkey>
+      <video href="2023.rail-1.4.mp4"/>
       <doi>10.18653/v1/2023.rail-1.4</doi>
     </paper>
     <paper id="5">
diff --git a/data/xml/2023.tacl.xml b/data/xml/2023.tacl.xml
index 5154e6037f..7ee3677dee 100644
--- a/data/xml/2023.tacl.xml
+++ b/data/xml/2023.tacl.xml
@@ -22,6 +22,7 @@
       <pages>1–17</pages>
       <url hash="b38684fe">2023.tacl-1.1</url>
       <bibkey>siriwardhana-etal-2023-improving</bibkey>
+      <video href="2023.tacl-1.1.mp4"/>
     </paper>
     <paper id="2">
       <title>Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement</title>
@@ -44,6 +45,7 @@
       <pages>34–48</pages>
       <url hash="e0f70734">2023.tacl-1.3</url>
       <bibkey>valvoda-etal-2023-role</bibkey>
+      <video href="2023.tacl-1.3.mp4"/>
     </paper>
     <paper id="4">
       <title>Meta-Learning a Cross-lingual Manifold for Semantic Parsing</title>
@@ -68,6 +70,7 @@
       <pages>68–84</pages>
       <url hash="69bd7885">2023.tacl-1.5</url>
       <bibkey>chen-etal-2023-opal</bibkey>
+      <video href="2023.tacl-1.5.mp4"/>
     </paper>
     <paper id="6">
       <title>Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation</title>
@@ -92,6 +95,7 @@
       <pages>102–121</pages>
       <url hash="42004046">2023.tacl-1.7</url>
       <bibkey>meister-etal-2023-locally</bibkey>
+      <video href="2023.tacl-1.7.mp4"/>
     </paper>
     <paper id="8">
       <title>Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization</title>
@@ -115,6 +119,7 @@
       <pages>139–156</pages>
       <url hash="4e9d7a5f">2023.tacl-1.9</url>
       <bibkey>majewska-etal-2023-cross</bibkey>
+      <video href="2023.tacl-1.9.mp4"/>
     </paper>
     <paper id="10">
       <title>Modeling Emotion Dynamics in Song Lyrics with State Space Models</title>
@@ -125,6 +130,7 @@
       <pages>157–175</pages>
       <url hash="7184a143">2023.tacl-1.10</url>
       <bibkey>song-beck-2023-modeling</bibkey>
+      <video href="2023.tacl-1.10.mp4"/>
     </paper>
     <paper id="11">
       <title><fixed-case>F</fixed-case>eeling<fixed-case>B</fixed-case>lue: A Corpus for Understanding the Emotional Connotation of Color in Context</title>
@@ -203,6 +209,7 @@
       <pages>267–283</pages>
       <url hash="bc7321bd">2023.tacl-1.16</url>
       <bibkey>chen-komachi-2023-discontinuous</bibkey>
+      <video href="2023.tacl-1.16.mp4"/>
     </paper>
     <paper id="17">
       <title>Efficient Long-Text Understanding with Short-Text Models</title>
@@ -292,6 +299,7 @@
       <pages>384–403</pages>
       <url hash="5d8863ed">2023.tacl-1.23</url>
       <bibkey>amini-etal-2023-naturalistic</bibkey>
+      <video href="2023.tacl-1.23.mp4"/>
     </paper>
     <paper id="24">
       <title>Tracking Brand-Associated Polarity-Bearing Topics in User Reviews</title>
@@ -420,6 +428,7 @@
       <pages>565–581</pages>
       <url hash="3349ba2f">2023.tacl-1.33</url>
       <bibkey>hong-etal-2023-visual-writing</bibkey>
+      <video href="2023.tacl-1.33.mp4"/>
     </paper>
     <paper id="34">
       <title>Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsing</title>
@@ -875,6 +884,7 @@
       <pages>1147–1161</pages>
       <url hash="a584faa7">2023.tacl-1.65</url>
       <bibkey>unanue-etal-2023-t3l</bibkey>
+      <video href="2023.tacl-1.65.mp4"/>
     </paper>
     <paper id="66">
       <title>Introduction to Mathematical Language Processing: Informal Proofs, Word Problems, and Supporting Tasks</title>
@@ -885,6 +895,7 @@
       <pages>1162–1184</pages>
       <url hash="f25ae2ed">2023.tacl-1.66</url>
       <bibkey>meadows-freitas-2023-introduction</bibkey>
+      <video href="2023.tacl-1.66.mp4"/>
     </paper>
     <paper id="67">
       <title>Evaluating a Century of Progress on the Cognitive Science of Adjective Ordering</title>
@@ -960,6 +971,7 @@
       <pages>1265–1282</pages>
       <url hash="b1258ac3">2023.tacl-1.72</url>
       <bibkey>huang-etal-2023-2</bibkey>
+      <video href="2023.tacl-1.72.mp4"/>
     </paper>
     <paper id="73">
       <title><fixed-case>PASTA</fixed-case>: A Dataset for Modeling <fixed-case>PA</fixed-case>rticipant <fixed-case>STA</fixed-case>tes in Narratives</title>
@@ -1063,6 +1075,7 @@
       <pages>1396–1415</pages>
       <url hash="ce32d0ca">2023.tacl-1.79</url>
       <bibkey>hu-etal-2023-multi-3</bibkey>
+      <video href="2023.tacl-1.79.mp4"/>
     </paper>
     <paper id="80">
       <title>Can Authorship Representation Learning Capture Stylistic Features?</title>
@@ -1103,6 +1116,7 @@
       <pages>1451–1470</pages>
       <url hash="eb3e52b6">2023.tacl-1.82</url>
       <bibkey>wilcox-etal-2023-testing</bibkey>
+      <video href="2023.tacl-1.82.mp4"/>
     </paper>
     <paper id="83">
       <title>Shared Lexical Items as Triggers of Code Switching</title>
@@ -1116,6 +1130,7 @@
       <pages>1471–1484</pages>
       <url hash="ec815dd6">2023.tacl-1.83</url>
       <bibkey>wintner-etal-2023-shared</bibkey>
+      <video href="2023.tacl-1.83.mp4"/>
     </paper>
     <paper id="84">
       <title>Learning More from Mixed Emotions: A Label Refinement Method for Emotion Recognition in Conversations</title>
@@ -1144,6 +1159,7 @@
       <pages>1500–1517</pages>
       <url hash="78675183">2023.tacl-1.85</url>
       <bibkey>guerreiro-etal-2023-hallucinations</bibkey>
+      <video href="2023.tacl-1.85.mp4"/>
     </paper>
     <paper id="86">
       <title><fixed-case>P</fixed-case>anini<fixed-case>QA</fixed-case>: Enhancing Patient Education Through Interactive Question Answering</title>
@@ -1164,6 +1180,7 @@
       <pages>1518–1536</pages>
       <url hash="432568f1">2023.tacl-1.86</url>
       <bibkey>cai-etal-2023-paniniqa</bibkey>
+      <video href="2023.tacl-1.86.mp4"/>
     </paper>
     <paper id="87">
       <title>Discover, Explain, Improve: An Automatic Slice Detection Benchmark for Natural Language Processing</title>
@@ -1178,6 +1195,7 @@
       <pages>1537–1552</pages>
       <url hash="fd62c952">2023.tacl-1.87</url>
       <bibkey>hua-etal-2023-discover</bibkey>
+      <video href="2023.tacl-1.87.mp4"/>
     </paper>
     <paper id="88">
       <title>Pre-train, Prompt, and Recommendation: A Comprehensive Survey of Language Modeling Paradigm Adaptations in Recommender Systems</title>
@@ -1189,6 +1207,7 @@
       <pages>1553–1571</pages>
       <url hash="3d7b6f96">2023.tacl-1.88</url>
       <bibkey>liu-etal-2023-pre</bibkey>
+      <video href="2023.tacl-1.88.mp4"/>
     </paper>
     <paper id="89">
       <title>An Efficient Self-Supervised Cross-View Training For Sentence Embedding</title>
@@ -1203,6 +1222,7 @@
       <pages>1572–1587</pages>
       <url hash="9769eef9">2023.tacl-1.89</url>
       <bibkey>limkonchotiwat-etal-2023-efficient</bibkey>
+      <video href="2023.tacl-1.89.mp4"/>
     </paper>
     <paper id="90">
       <title>General then Personal: Decoupling and Pre-training for Personalized Headline Generation</title>
@@ -1215,6 +1235,7 @@
       <pages>1588–1607</pages>
       <url hash="cd6acd30">2023.tacl-1.90</url>
       <bibkey>song-etal-2023-general</bibkey>
+      <video href="2023.tacl-1.90.mp4"/>
     </paper>
     <paper id="91">
       <title>Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training</title>
@@ -1233,6 +1254,7 @@
       <pages>1608–1623</pages>
       <url hash="9e46f120">2023.tacl-1.91</url>
       <bibkey>zhu-etal-2023-removing</bibkey>
+      <video href="2023.tacl-1.91.mp4"/>
     </paper>
     <paper id="92">
       <title>Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation</title>
@@ -1252,6 +1274,7 @@
       <pages>1643–1668</pages>
       <url hash="39a0e411">2023.tacl-1.92</url>
       <bibkey>fernandes-etal-2023-bridging</bibkey>
+      <video href="2023.tacl-1.92.mp4"/>
     </paper>
     <paper id="93">
       <title><fixed-case>A</fixed-case>fri<fixed-case>S</fixed-case>peech-200: Pan-<fixed-case>A</fixed-case>frican Accented Speech Dataset for Clinical and General Domain <fixed-case>ASR</fixed-case></title>
@@ -1271,6 +1294,7 @@
       <pages>1669–1685</pages>
       <url hash="0cd420af">2023.tacl-1.93</url>
       <bibkey>olatunji-etal-2023-afrispeech</bibkey>
+      <video href="2023.tacl-1.93.mp4"/>
     </paper>
     <paper id="94">
       <title><fixed-case>M</fixed-case>iss<fixed-case>M</fixed-case>odal: Increasing Robustness to Missing Modality in Multimodal Sentiment Analysis</title>
@@ -1281,6 +1305,7 @@
       <pages>1686–1702</pages>
       <url hash="75d65e3b">2023.tacl-1.94</url>
       <bibkey>lin-hu-2023-missmodal</bibkey>
+      <video href="2023.tacl-1.94.mp4"/>
     </paper>
     <paper id="95">
       <title>Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision</title>
@@ -1298,6 +1323,7 @@
       <pages>1703–1718</pages>
       <url hash="dc8c98b8">2023.tacl-1.95</url>
       <bibkey>kharitonov-etal-2023-speak</bibkey>
+      <video href="2023.tacl-1.95.mp4"/>
     </paper>
     <paper id="96">
       <title><fixed-case>R</fixed-case>e<fixed-case>COGS</fixed-case>: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation</title>
@@ -1309,6 +1335,7 @@
       <pages>1719–1733</pages>
       <url hash="098e9057">2023.tacl-1.96</url>
       <bibkey>wu-etal-2023-recogs</bibkey>
+      <video href="2023.tacl-1.96.mp4"/>
     </paper>
     <paper id="97">
       <title>Data-driven Parsing Evaluation for Child-Parent Interactions</title>
@@ -1336,6 +1363,7 @@
       <pages>1754–1771</pages>
       <url hash="cd6e4624">2023.tacl-1.98</url>
       <bibkey>agrawal-etal-2023-qameleon</bibkey>
+      <video href="2023.tacl-1.98.mp4"/>
     </paper>
   </volume>
 </collection>
diff --git a/data/xml/2024.cl.xml b/data/xml/2024.cl.xml
index 522df380d4..016a34b47c 100644
--- a/data/xml/2024.cl.xml
+++ b/data/xml/2024.cl.xml
@@ -19,6 +19,7 @@
       <pages>1–24</pages>
       <url hash="350741f4">2024.cl-1.1</url>
       <bibkey>palmer-2024-big</bibkey>
+      <video href="2024.cl-1.2.mp4"/>
     </paper>
     <paper id="2">
       <title>Rethinking the Exploitation of Monolingual Data for Low-Resource Neural Machine Translation</title>
@@ -34,6 +35,7 @@
       <pages>25–47</pages>
       <url hash="97fc3d67">2024.cl-1.2</url>
       <bibkey>pang-etal-2024-rethinking</bibkey>
+      <video href="2024.cl-1.2.mp4"/>
     </paper>
     <paper id="3">
       <title>How Is a “Kitchen Chair” like a “Farm Horse”? Exploring the Representation of Noun-Noun Compound Semantics in Transformer-based Language Models</title>
@@ -45,6 +47,7 @@
       <pages>49–81</pages>
       <url hash="0aff206a">2024.cl-1.3</url>
       <bibkey>ormerod-etal-2024-kitchen</bibkey>
+      <video href="2024.cl-1.3.mp4"/>
     </paper>
     <paper id="4">
       <title>Universal Generation for <fixed-case>O</fixed-case>ptimality <fixed-case>T</fixed-case>heory Is <fixed-case>PSPACE</fixed-case>-Complete</title>
@@ -54,6 +57,7 @@
       <pages>83–117</pages>
       <url hash="59b66d33">2024.cl-1.4</url>
       <bibkey>hao-2024-universal</bibkey>
+      <video href="2024.cl-1.4.mp4"/>
     </paper>
     <paper id="5">
       <title>Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering</title>
@@ -67,6 +71,7 @@
       <pages>119–155</pages>
       <url hash="1e92522f">2024.cl-1.5</url>
       <bibkey>chaturvedi-etal-2024-analyzing</bibkey>
+      <video href="2024.cl-1.5.mp4"/>
     </paper>
     <paper id="6">
       <title>On the Role of Morphological Information for Contextual Lemmatization</title>
diff --git a/data/xml/2024.eacl.xml b/data/xml/2024.eacl.xml
index 5c0b3e2e01..a12319790a 100644
--- a/data/xml/2024.eacl.xml
+++ b/data/xml/2024.eacl.xml
@@ -3627,11 +3627,58 @@
     <meta>
       <title>The 18th Conference of the European Chapter of the Association for Computational Linguistics</title>
       <location>St. Julian’s, Malta</location>
-      <dates>March, 2024</dates>
+      <dates>March 17-22, 2024</dates>
     </meta>
     <links>
       <url type="website">https://2024.eacl.org</url>
+      <url type="handbook">2024.eacl.handbook.pdf</url>
     </links>
+
+    <talk>
+      <title>Karen Spärck Jones Award Lecture: Human vs. Generative <fixed-case>AI</fixed-case> in Content Creation Competition: Symbiosis or Conflict?</title>
+      <speaker><first>Hongning</first><last>Wang</last></speaker>
+      <url type="video">2024.eacl.invited.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 1: Quality Data for <fixed-case>LLM</fixed-case>s: Challenges and Opportunities for <fixed-case>NLP</fixed-case></title>
+      <speaker><first>Hinrich</first><last>Schütze</last></speaker>
+      <url type="video">2024.eacl.keynote1.mp4</url>
+    </talk>
+    <talk>
+      <title>Keynote 2: Prompting is not all you need! Or why Structure and Representations still matter in <fixed-case>NLP</fixed-case></title>
+      <speaker><first>Mirella</first><last>Lapata</last></speaker>
+      <url type="video">2024.eacl.keynote2.mp4</url>
+    </talk>
+    <talk>
+      <title>Opening Session</title>
+      <speaker><first>Michael</first><last>Strube</last></speaker>
+      <speaker><first>Matthew</first><last>Purver</last></speaker>
+      <speaker><first>Claudia</first><last>Borg</last></speaker>
+      <speaker><first>Haiming</first><last>Liu</last></speaker>
+      <url type="video">2024.eacl.opening-session.mp4</url>
+    </talk>
+    <talk>
+      <title>Business Meeting</title>
+      <speaker><first>Preslav</first><last>Nakov</last></speaker>
+      <speaker><first>Roberto</first><last>Basili</last></speaker>
+      <speaker><first>Haiming</first><last>Liu</last></speaker>
+      <speaker><first>Matthew</first><last>Purver</last></speaker>
+      <url type="video">2024.eacl.business-meeting.mp4</url>
+    </talk>
+    <talk>
+      <title>Best Papers Awards Session</title>
+      <speaker><first>Barbara</first><last>Plank</last></speaker>
+      <url type="video">2024.eacl.best-papers.mp4</url>
+    </talk>
+    <talk>
+      <title>Closing Session</title>
+      <speaker><first>Yvette</first><last>Graham</last></speaker>
+      <speaker><first>Michael</first><last>Strube</last></speaker>
+      <speaker><first>Preslav</first><last>Nakov</last></speaker>
+      <speaker><first>Mark</first><last>Finlayson</last></speaker>
+      <speaker><first>Barbara</first><last>Plank</last></speaker>
+      <url type="video">2024.eacl.closing-session.mp4</url>
+    </talk>
     <colocated>
       <volume-id>2024.findings-eacl</volume-id>
       <volume-id>2024.caldpseudo-1</volume-id>
diff --git a/data/xml/2024.sigtyp.xml b/data/xml/2024.sigtyp.xml
index f9de00f525..9f916d86d9 100644
--- a/data/xml/2024.sigtyp.xml
+++ b/data/xml/2024.sigtyp.xml
@@ -36,6 +36,7 @@
       <abstract>Human processing of nonlocal syntactic dependencies requires the engagement of limited working memory for encoding, maintenance, and retrieval. This process creates an evolutionary pressure for language to be structured in a way that keeps the subparts of a dependency closer to each other, an efficiency principle termed dependency locality. The current study proposes that such a dependency locality pressure can be modulated by the surprisal of the antecedent, defined as the first part of a dependency, due to strategic allocation of working memory. In particular, antecedents with novel and unpredictable information are prioritized for memory encoding, receiving more robust representation against memory interference and decay, and thus are more capable of handling longer dependency length. We examine this claim by analyzing dependency corpora of 11 languages, with word surprisal generated from GPT-3 language model. In support of our hypothesis, we find evidence for a positive correlation between dependency length and the antecedent surprisal in most of the languages in our analyses. A closer look into the dependencies with core arguments shows that this correlation consistently holds for subject relations but not for object relations.</abstract>
       <url hash="74e339b6">2024.sigtyp-1.1</url>
       <bibkey>xu-futrell-2024-syntactic</bibkey>
+      <video href="2024.sigtyp-1.1.mp4"/>
     </paper>
     <paper id="2">
       <title><fixed-case>GUIDE</fixed-case>: Creating Semantic Domain Dictionaries for Low-Resource Languages</title>
@@ -47,6 +48,7 @@
       <abstract>Over 7,000 of the world’s 7,168 living languages are still low-resourced. This paper aims to narrow the language documentation gap by creating multiparallel dictionaries, clustered by SIL’s semantic domains. This task is new for machine learning and has previously been done manually by native speakers. We propose GUIDE, a language-agnostic tool that uses a GNN to create and populate semantic domain dictionaries, using seed dictionaries and Bible translations as a parallel text corpus. Our work sets a new benchmark, achieving an exemplary average precision of 60% in eight zero-shot evaluation languages and predicting an average of 2,400 dictionary entries. We share the code, model, multilingual evaluation data, and new dictionaries with the research community: https://github.com/janetzki/GUIDE</abstract>
       <url hash="2efc4e41">2024.sigtyp-1.2</url>
       <bibkey>janetzki-etal-2024-guide</bibkey>
+      <video href="2024.sigtyp-1.2.mp4"/>
     </paper>
     <paper id="3">
       <title>A New Dataset for Tonal and Segmental Dialectometry from the <fixed-case>Y</fixed-case>ue- and Pinghua-Speaking Area</title>
@@ -57,6 +59,7 @@
       <abstract>Traditional dialectology or dialect geography is the study of geographical variation of language. Originated in Europe and pioneered in Germany and France, this field has predominantly been focusing on sounds, more specifically, on segments. Similarly, quantitative approaches to language variation concerned with the phonetic level are in most cases focusing on segments as well. However, more than half of the world’s languages include lexical tones (Yip, 2002). Despite this, tones are still underexplored in quantitative language comparison, partly due to the low accessibility of the suitable data. This paper aims to introduce a newly digitised dataset which comes from the Yue- and Pinghua-speaking areas in Southern China, with over 100 dialects. This dataset consists of two parts: tones and segments. In this paper, we illustrate how we can computationaly model tones in order to explore linguistic variation. We have applied a tone distance metric on our data, and we have found that 1) dialects also form a continuum on the tonal level and 2) other than tonemic (inventory) and tonetic differences, dialects can also differ in the lexical distribution of tones. The availability of this dataset will hopefully enable further exploration of the role of tones in quantitative typology and NLP research.</abstract>
       <url hash="529d3082">2024.sigtyp-1.3</url>
       <bibkey>sung-etal-2024-new</bibkey>
+      <video href="2024.sigtyp-1.3.mp4"/>
     </paper>
     <paper id="4">
       <title>A Computational Model for the Assessment of Mutual Intelligibility Among Closely Related Languages</title>
@@ -66,6 +69,7 @@
       <abstract>Closely related languages show linguistic similarities that allow speakers of one language to understand speakers of another language without having actively learned it. Mutual intelligibility varies in degree and is typically tested in psycholinguistic experiments. To study mutual intelligibility computationally, we propose a computer-assisted method using the Linear Discriminative Learner, a computational model developed to approximate the cognitive processes by which humans learn languages, which we expand with multilingual semantic vectors and multilingual sound classes. We test the model on cognate data from German, Dutch, and English, three closely related Germanic languages. We find that our model’s comprehension accuracy depends on 1) the automatic trimming of inflections and 2) the language pair for which comprehension is tested. Our multilingual modelling approach does not only offer new methodological findings for automatic testing of mutual intelligibility across languages but also extends the use of Linear Discriminative Learning to multilingual settings.</abstract>
       <url hash="7f625753">2024.sigtyp-1.4</url>
       <bibkey>nieder-list-2024-computational</bibkey>
+      <video href="2024.sigtyp-1.4.mp4"/>
     </paper>
     <paper id="5">
       <title>Predicting <fixed-case>M</fixed-case>andarin and <fixed-case>C</fixed-case>antonese Adult Speakers’ Eye-Movement Patterns in Natural Reading</title>
@@ -77,6 +81,7 @@
       <abstract>Please find the attached PDF file for the extended abstract of our study.</abstract>
       <url hash="3d11da57">2024.sigtyp-1.5</url>
       <bibkey>junlin-etal-2024-predicting</bibkey>
+      <video href="2024.sigtyp-1.5.mp4"/>
     </paper>
     <paper id="6">
       <title>The Typology of Ellipsis: A Corpus for Linguistic Analysis and Machine Learning Applications</title>
@@ -107,6 +112,7 @@
       <abstract>This paper lays the groundwork for initiating research into Source Language Identification; the task of identifying the original language of a machine-translated text. We contribute a dataset of translations from a typologically diverse spectrum of languages into English and use it to set initial baselines for this novel task.</abstract>
       <url hash="5ad46947">2024.sigtyp-1.8</url>
       <bibkey>reijnaers-pouw-2024-gtnc</bibkey>
+      <video href="2024.sigtyp-1.8.mp4"/>
     </paper>
     <paper id="9">
       <title>Sociolinguistically Informed Interpretability: A Case Study on <fixed-case>H</fixed-case>inglish Emotion Classification</title>
@@ -130,6 +136,7 @@
       <abstract>In order to draw generalizable conclusions about the performance of multilingual models across languages, it is important to evaluate on a set of languages that captures linguistic diversity.Linguistic typology is increasingly used to justify language selection, inspired by language sampling in linguistics.However, justifications for ‘typological diversity’ exhibit great variation, as there seems to be no set definition, methodology or consistent link to linguistic typology.In this work, we provide a systematic insight into how previous work in the ACL Anthology uses the term ‘typological diversity’.Our two main findings are: 1) what is meant by typologically diverse language selection is not consistent and 2) the actual typological diversity of the language sets in these papers varies greatly.We argue that, when making claims about ‘typological diversity’, an operationalization of this should be included.A systematic approach that quantifies this claim, also with respect to the number of languages used, would be even better.</abstract>
       <url hash="4ae14aa8">2024.sigtyp-1.10</url>
       <bibkey>poelman-etal-2024-call</bibkey>
+      <video href="2024.sigtyp-1.10.mp4"/>
     </paper>
     <paper id="11">
       <title>Are Sounds Sound for Phylogenetic Reconstruction?</title>
@@ -167,6 +174,7 @@
       <abstract>While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-tuned for automatic speech recognition (ASR), downstream performance can still be relatively poor on languages that are under-represented in the pre-training data. Continued pre-training on 70–200 hours of untranscribed speech in these languages can help — but what about languages without that much recorded data? For such cases, we show that supplementing the target language with data from a similar, higher-resource ‘donor’ language can help. For example, continued pretraining on only 10 hours of low-resource Punjabi supplemented with 60 hours of donor Hindi is almost as good as continued pretraining on 70 hours of Punjabi. By contrast, sourcing supplemental data from less similar donors like Bengali does not improve ASR performance. To inform donor language selection, we propose a novel similarity metric based on the sequence distribution of induced acoustic units: the Acoustic Token Distribution Similarity (ATDS). Across a set of typologically different target languages (Punjabi, Galician, Iban, Setswana), we show that the ATDS between the target language and its candidate donors precisely predicts target language ASR performance.</abstract>
       <url hash="fda5588c">2024.sigtyp-1.13</url>
       <bibkey>san-etal-2024-predicting</bibkey>
+      <video href="2024.sigtyp-1.13.mp4"/>
     </paper>
     <paper id="14">
       <title><fixed-case>M</fixed-case>ode<fixed-case>L</fixed-case>ing: A Novel Dataset for Testing Linguistic Reasoning in Language Models</title>
@@ -182,6 +190,7 @@
       <abstract>Large language models (LLMs) perform well on (at least) some evaluations of both few-shot multilingual adaptation and reasoning. However, evaluating the intersection of these two skills—multilingual few-shot reasoning—is difficult: even relatively low-resource languages can be found in large training corpora, raising the concern that when we intend to evaluate a model’s ability to generalize to a new language, that language may have in fact been present during the model’s training. If such language contamination has occurred, apparent cases of few-shot reasoning could actually be due to memorization. Towards understanding the capability of models to perform multilingual few-shot reasoning, we propose modeLing, a benchmark of Rosetta stone puzzles. This type of puzzle, originating from competitions called Linguistics Olympiads, contain a small number of sentences in a target language not previously known to the solver. Each sentence is translated to the solver’s language such that the provided sentence pairs uniquely specify a single most reasonable underlying set of rules; solving requires applying these rules to translate new expressions (Figure 1). modeLing languages are chosen to be extremely low-resource such that the risk of training data contamination is low, and unlike prior datasets, it consists entirely of problems written specifically for this work, as a further measure against data leakage. Empirically, we find evidence that popular LLMs do not have data leakage on our benchmark.</abstract>
       <url hash="08504410">2024.sigtyp-1.14</url>
       <bibkey>chi-etal-2024-modeling</bibkey>
+      <video href="2024.sigtyp-1.14.mp4"/>
     </paper>
     <paper id="15">
       <title><fixed-case>T</fixed-case>artu<fixed-case>NLP</fixed-case> @ <fixed-case>SIGTYP</fixed-case> 2024 Shared Task: Adapting <fixed-case>XLM</fixed-case>-<fixed-case>R</fixed-case>o<fixed-case>BERT</fixed-case>a for Ancient and Historical Languages</title>
@@ -191,6 +200,7 @@
       <abstract>We present our submission to the unconstrained subtask of the SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages for morphological annotation, POS-tagging, lemmatization, characterand word-level gap-filling. We developed a simple, uniform, and computationally lightweight approach based on the adapters framework using parameter-efficient fine-tuning. We applied the same adapter-based approach uniformly to all tasks and 16 languages by fine-tuning stacked language- and task-specific adapters. Our submission obtained an overall second place out of three submissions, with the first place in word-level gap-filling. Our results show the feasibility of adapting language models pre-trained on modern languages to historical and ancient languages via adapter training.</abstract>
       <url hash="24674b78">2024.sigtyp-1.15</url>
       <bibkey>dorkin-sirts-2024-tartunlp</bibkey>
+      <video href="2024.sigtyp-1.15.mp4"/>
     </paper>
     <paper id="16">
       <title>Heidelberg-Boston @ <fixed-case>SIGTYP</fixed-case> 2024 Shared Task: Enhancing Low-Resource Language Analysis With Character-Aware Hierarchical Transformers</title>
@@ -200,6 +210,7 @@
       <abstract>Historical languages present unique challenges to the NLP community, with one prominent hurdle being the limited resources available in their closed corpora. This work describes our submission to the constrained subtask of the SIGTYP 2024 shared task, focusing on PoS tagging, morphological tagging, and lemmatization for 13 historical languages. For PoS and morphological tagging we adapt a hierarchical tokenization method from Sun et al. (2023) and combine it with the advantages of the DeBERTa-V3 architecture, enabling our models to efficiently learn from every character in the training data. We also demonstrate the effectiveness of characterlevel T5 models on the lemmatization task. Pre-trained from scratch with limited data, our models achieved first place in the constrained subtask, nearly reaching the performance levels of the unconstrained task’s winner. Our code is available at https://github.com/bowphs/ SIGTYP-2024-hierarchical-transformers</abstract>
       <url hash="30d2fdd3">2024.sigtyp-1.16</url>
       <bibkey>riemenschneider-krahn-2024-heidelberg</bibkey>
+      <video href="2024.sigtyp-1.16.mp4"/>
     </paper>
     <paper id="17">
       <title><fixed-case>UDP</fixed-case>arse @ <fixed-case>SIGTYP</fixed-case> 2024 Shared Task : Modern Language Models for Historical Languages</title>
@@ -208,6 +219,7 @@
       <abstract>SIGTYP’s Shared Task on Word Embedding Evaluation for Ancient and Historical Languages was proposed in two variants, constrained or unconstrained. Whereas the constrained variant disallowed any other data to train embeddings or models than the data provided, the unconstrained variant did not have these limits. We participated in the five tasks of the unconstrained variant and came out first. The tasks were the prediction of part-of-speech, lemmas and morphological features and filling masked words and masked characters on 16 historical languages. We decided to use a dependency parser and train the data using an underlying pretrained transformer model to predict part-of-speech tags, lemmas, and morphological features. For predicting masked words, we used multilingual distilBERT (with rather bad results). In order to predict masked characters, our language model is extremely small: it is a model of 5-gram frequencies, obtained by reading the available training data.</abstract>
       <url hash="128752d0">2024.sigtyp-1.17</url>
       <bibkey>heinecke-2024-udparse</bibkey>
+      <video href="2024.sigtyp-1.17.mp4"/>
     </paper>
     <paper id="18">
       <title><fixed-case>A</fixed-case>llen Institute for <fixed-case>AI</fixed-case> @ <fixed-case>SIGTYP</fixed-case> 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages</title>
diff --git a/data/xml/2024.tacl.xml b/data/xml/2024.tacl.xml
index c36ce91216..b28b524ab7 100644
--- a/data/xml/2024.tacl.xml
+++ b/data/xml/2024.tacl.xml
@@ -22,6 +22,7 @@
       <pages>1–18</pages>
       <url hash="190d51f6">2024.tacl-1.1</url>
       <bibkey>glockner-etal-2024-ambifc</bibkey>
+      <video href="2024.tacl-1.1.mp4"/>
     </paper>
     <paper id="2">
       <title>Language Varieties of <fixed-case>I</fixed-case>taly: Technology Challenges and Opportunities</title>
@@ -31,6 +32,7 @@
       <pages>19–38</pages>
       <url hash="dd061bfb">2024.tacl-1.2</url>
       <bibkey>ramponi-2024-language</bibkey>
+      <video href="2024.tacl-1.2.mp4"/>
     </paper>
     <paper id="3">
       <title>Benchmarking Large Language Models for News Summarization</title>
@@ -45,6 +47,7 @@
       <pages>39–57</pages>
       <url hash="2e4604d4">2024.tacl-1.3</url>
       <bibkey>zhang-etal-2024-benchmarking</bibkey>
+      <video href="2024.tacl-1.3.mp4"/>
     </paper>
     <paper id="4">
       <title>m<fixed-case>GPT</fixed-case>: Few-Shot Learners Go Multilingual</title>
@@ -59,6 +62,7 @@
       <pages>58–79</pages>
       <url hash="ad281290">2024.tacl-1.4</url>
       <bibkey>shliazhko-etal-2024-mgpt</bibkey>
+      <video href="2024.tacl-1.4.mp4"/>
     </paper>
     <paper id="5">
       <title>Cultural Adaptation of Recipes</title>
@@ -322,6 +326,7 @@
       <pages>432–448</pages>
       <url hash="8df122c2">2024.tacl-1.24</url>
       <bibkey>agrawal-carpuat-2024-text</bibkey>
+      <video href="2024.tacl-1.24.mp4"/>
     </paper>
     <paper id="25">
       <title>Simultaneous Selection and Adaptation of Source Data via Four-Level Optimization</title>
@@ -408,6 +413,7 @@
       <pages>562–575</pages>
       <url hash="a0c93cad">2024.tacl-1.31</url>
       <bibkey>staniek-etal-2024-text</bibkey>
+      <video href="2024.tacl-1.31.mp4"/>
     </paper>
     <paper id="32">
       <title>Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions</title>