encoder.json

[
    {
        "paper_title": "From Word Embeddings to Document Distances",
        "paper_link": "http://jmlr.org/proceedings/papers/v37/kusnerb15.pdf",
        "name": "Word Mover's Distance",
        "code": [
            {
                "language": "C, Python",
                "link": "https://github.com/mkusner/wmd",
                "pretrained": false
            }
        ],
        "s2_paper_id": "2871f115e7a11c903258491c75d4171fac679344"
    },
    {
        "paper_title": "Distributed Representations of Sentences and Documents",
        "paper_link": "https://arxiv.org/abs/1405.4053",
        "name": "Doc2Vec",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/inejc/paragraph-vectors",
                "unofficial": true
            },
            {
                "language": "Python",
                "link": "https://github.com/jhlau/doc2vec",
                "unofficial": true,
                "pretrained": true
            }
        ]
    },
    {
        "paper_title": "Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models",
        "paper_link": "https://arxiv.org/abs/1411.2539",
        "name": "VSE",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/ryankiros/visual-semantic-embedding"
            },
            {
                "language": "Pytorch",
                "link": "https://github.com/linxd5/VSE_Pytorch",
                "unofficial": true,
                "load_pretrained": true
            }
        ]
    },
    {
        "paper_title": "Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books",
        "paper_link": "https://arxiv.org/abs/1506.06724",
        "name": "SkipThought",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/ryankiros/skip-thoughts"
            },
            {
                "language": "TF",
                "link": "https://github.com/tensorflow/models/tree/master/research/skip_thoughts",
                "unofficial": true,
                "pretrained": true
            },
            {
                "language": "Pytorch, Torch",
                "link": "https://github.com/Cadene/skip-thoughts.torch",
                "unofficial": true,
                "load_pretrained": true
            }
        ]
    },
    {
        "paper_title": "Order-Embeddings of Images and Language",
        "paper_link": "https://arxiv.org/abs/1511.06361",
        "name": "order-embedding",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/ivendrov/order-embedding"
            }
        ]
    },
    {
        "paper_title": "Towards Universal Paraphrastic Sentence Embeddings",
        "paper_link": "https://arxiv.org/abs/1511.08198",
        "name": "ParagramPhrase",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/jwieting/iclr2016"
            }
        ]
    },
    {
        "paper_title": "Learning Distributed Representations of Sentences from Unlabelled Data",
        "paper_link": "https://arxiv.org/abs/1602.03483",
        "name": "FastSent",
        "code": [
            {
                "language": "Python",
                "link": "https://github.com/fh295/SentenceRepresentation"
            }
        ]
    },
    {
        "paper_title": "Charagram: Embedding Words and Sentences via Character n-grams",
        "paper_link": "https://arxiv.org/abs/1607.02789",
        "name": "Charagram",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/jwieting/charagram"
            }
        ]
    },
    {
        "paper_title": "Learning Generic Sentence Representations Using Convolutional Neural Networks",
        "paper_link": "https://arxiv.org/abs/1611.07897",
        "name": "ConvSent",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/zhegan27/ConvSent",
                "pretrained": false
            }
        ]
    },
    {
        "paper_title": "Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features",
        "paper_link": "https://arxiv.org/abs/1703.02507",
        "name": "Sent2Vec",
        "code": [
            {
                "language": "C++",
                "link": "https://github.com/epfml/sent2vec"
            }
        ]
    },
    {
        "paper_title": "Learning to Generate Reviews and Discovering Sentiment",
        "paper_link": "https://arxiv.org/abs/1704.01444",
        "name": "Sentiment Neuron",
        "code": [
            {
                "language": "TF",
                "link": "https://github.com/openai/generating-reviews-discovering-sentiment"
            },
            {
                "language": "Pytorch",
                "link": "https://github.com/guillitte/pytorch-sentiment-neuron",
                "unofficial": true,
                "load_pretrained": true
            },
            {
                "language": "Pytorch",
                "link": "https://github.com/NVIDIA/sentiment-discovery",
                "unofficial": true,
                "pretrained": true
            }
        ]
    },
    {
        "paper_title": "Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings",
        "paper_link": "https://arxiv.org/abs/1705.00364",
        "name": "GRAN",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/jwieting/acl2017"
            }
        ]
    },
    {
        "paper_title": "Supervised Learning of Universal Sentence Representations from Natural Language Inference Data",
        "paper_link": "https://arxiv.org/abs/1705.02364",
        "name": "InferSent",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/facebookresearch/InferSent"
            }
        ]
    },
    {
        "paper_title": "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives",
        "paper_link": "https://arxiv.org/abs/1707.05612",
        "name": "VSE++",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/fartashf/vsepp"
            }
        ]
    },
    {
        "paper_title": "Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm",
        "paper_link": "https://arxiv.org/abs/1708.00524",
        "name": "DeepMoji",
        "code": [
            {
                "language": "Keras",
                "link": "https://github.com/bfelbo/DeepMoji"
            },
            {
                "language": "Pytorch",
                "link": "https://github.com/huggingface/torchMoji",
                "load_pretrained": true
            }
        ]
    },
    {
        "paper_title": "StarSpace: Embed All The Things!",
        "paper_link": "https://arxiv.org/abs/1709.03856",
        "name": "StarSpace",
        "code": [
            {
                "language": "C++",
                "link": "https://github.com/facebookresearch/StarSpace"
            }
        ]
    },
    {
        "paper_title": "DisSent: Learning Sentence Representations from Explicit Discourse Relations",
        "paper_link": "https://arxiv.org/abs/1710.04334",
        "name": "DisSent",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/windweller/DisExtract",
                "email_for_pretrained": true
            }
        ]
    },
    {
        "paper_title": "Dual-Path Convolutional Image-Text Embedding with Instance Loss",
        "paper_link": "https://arxiv.org/abs/1711.05535",
        "name": "Image-Text-Embedding",
        "code": [
            {
                "language": "Matlab",
                "link": "https://github.com/layumi/Image-Text-Embedding"
            }
        ]
    },
    {
        "paper_title": "Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations",
        "paper_link": "https://arxiv.org/abs/1711.05732",
        "name": "para-nmt",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/jwieting/para-nmt-50m"
            }
        ]
    },
    {
        "paper_title": "An efficient framework for learning sentence representations",
        "paper_link": "https://arxiv.org/abs/1803.02893",
        "name": "Quick-Thought",
        "code": [
            {
                "language": "TF",
                "link": "https://github.com/lajanugen/S2V"
            }
        ]
    },
    {
        "paper_title": "Universal Sentence Encoder",
        "paper_link": "https://arxiv.org/abs/1803.11175",
        "name": "USE",
        "code": [
            {
                "language": "TF-Hub",
                "link": "https://tfhub.dev/google/universal-sentence-encoder-large/2",
                "no_training_code": true
            }
        ]
    },
    {
        "paper_title": "Learning general purpose distributed sentence representations via large scale multi-task learning",
        "paper_link": "https://arxiv.org/abs/1804.00079",
        "name": "GenSen",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/Maluuba/gensen"
            }
        ]
    },
    {
        "paper_title": "End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions",
        "paper_link": "https://arxiv.org/abs/1804.08813",
        "name": "DEISTE",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/yinwenpeng/SciTail"
            }
        ]
    },
    {
        "paper_title": "Embedding Text in Hyperbolic Spaces",
        "paper_link": "https://arxiv.org/abs/1806.04313",
        "name": "HyperText",
        "code": [
            {
                "language": "TF",
                "link": "https://github.com/brain-research/hyperbolictext",
                "pretrained": false
            }
        ]
    },
    {
        "paper_title": "Representation Learning with Contrastive Predictive Coding",
        "paper_link": "https://arxiv.org/abs/1807.03748",
        "name": "CPC",
        "code": [
            {
                "language": "Keras",
                "link": "https://github.com/davidtellez/contrastive-predictive-coding",
                "unofficial": true
            }
        ]
    },
    {
        "paper_title": "Context Mover\u2019s Distance & Barycenters: Optimal transport of contexts for building representations",
        "paper_link": "https://arxiv.org/abs/1808.09663",
        "name": "CMD",
        "code": [
            {
                "language": "Python",
                "link": "https://github.com/context-mover/context-mover-distance-and-barycenters"
            }
        ]
    },
    {
        "paper_title": "Learning Universal Sentence Representations with Mean-Max Attention Autoencoder",
        "paper_link": "https://arxiv.org/abs/1809.06590",
        "name": "Mean-MaxAAE",
        "code": [
            {
                "language": "TF",
                "link": "https://github.com/Zminghua/SentEncoding"
            }
        ]
    },
    {
        "paper_title": "Improving Sentence Representations with Consensus Maximisation",
        "paper_link": "https://arxiv.org/abs/1810.01064",
        "name": "Multi-view"
    },
    {
        "paper_title": "BioSentVec: creating sentence embeddings for biomedical texts",
        "paper_link": "https://arxiv.org/abs/1810.09302",
        "name": "BioSentVec",
        "code": [
            {
                "language": "Python",
                "link": "https://github.com/ncbi-nlp/BioSentVec"
            }
        ]
    },
    {
        "paper_title": "Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model",
        "paper_link": "https://arxiv.org/abs/1810.12836",
        "name": "USE-xling",
        "code": [
            {
                "language": "TF-Hub",
                "link": "https://tfhub.dev/s?q=universal-sentence-encoder-xling",
                "no_training_code": true
            }
        ]
    },
    {
        "paper_title": "Word Mover's Embedding: From Word2Vec to Document Embedding",
        "paper_link": "https://arxiv.org/abs/1811.01713",
        "name": "WordMoversEmbeddings",
        "code": [
            {
                "language": "C, Python",
                "link": "https://github.com/IBM/WordMoversEmbeddings",
                "pretrained": false
            }
        ]
    },
    {
        "paper_title": "A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks",
        "paper_link": "https://arxiv.org/abs/1811.06031",
        "name": "HMTL",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/huggingface/hmtl"
            }
        ]
    },
    {
        "paper_title": "Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond",
        "paper_link": "https://arxiv.org/abs/1812.10464",
        "name": "LASER",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/facebookresearch/LASER"
            }
        ]
    },
    {
        "paper_title": "No Training Required: Exploring Random Encoders for Sentence Classification",
        "paper_link": "https://arxiv.org/abs/1901.10444",
        "name": "randsent",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/facebookresearch/randsent",
                "pretrained": false
            }
        ]
    },
    {
        "paper_title": "CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model",
        "paper_link": "https://arxiv.org/abs/1902.06423",
        "name": "CMOW",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/florianmai/word2mat",
                "pretrained": false
            }
        ]
    },
    {
        "paper_title": "Multilingual Universal Sentence Encoder",
        "paper_link": "https://arxiv.org/abs/1907.04307",
        "name": "MultilingualUSE",
        "code": [
            {
                "language": "TF-Hub",
                "link": "https://tfhub.dev/google/universal-sentence-encoder-multilingual/1",
                "no_training_code": true
            }
        ]
    },
    {
        "paper_title": "GLOSS: Generative Latent Optimization of Sentence Representations",
        "paper_link": "https://arxiv.org/abs/1907.06385",
        "name": "GLOSS"
    },
    {
        "paper_title": "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
        "paper_link": "https://arxiv.org/abs/1908.10084",
        "name": "Sentence-BERT",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/UKPLab/sentence-transformers",
                "pretrained": true
            }
        ]
    },
    {
        "paper_title": "SBERT-WK: A Sentence Embedding Method By Dissecting BERT-based Word Models",
        "paper_link": "https://arxiv.org/abs/2002.06652",
        "name": "SBERT-WK",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/BinWang28/SBERT-WK-Sentence-Embedding",
                "pretrained": true
            }
        ]
    },
    {
        "paper_title": "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations",
        "paper_link": "https://arxiv.org/abs/2006.03659",
        "name": "DeCLUTR",
        "code": [
            {
                "language": "Pytorch",
                "link": "https://github.com/JohnGiorgi/DeCLUTR"
            }
        ]
    },
    {
        "paper_title": "Language-agnostic BERT Sentence Embedding",
        "paper_link": "https://arxiv.org/abs/2007.01852",
        "name": "LaBSE",
        "code": [
            {
                "language": "TF-Hub",
                "link": "https://tfhub.dev/google/LaBSE/1",
                "no_training_code": true
            }
        ]
    },
    {
        "paper_title": "On the Sentence Embeddings from Pre-trained Language Models",
        "paper_link": "https://arxiv.org/abs/2011.05864",
        "name": "BERT-flow",
        "code": [
            {
                "language": "TF",
                "link": "https://github.com/bohanli/BERT-flow",
                "pretrained": true
            }
        ]
    },
    {
        "paper_title": "Convolutional Neural Network for Universal Sentence Embeddings",
        "paper_link": "https://pdfs.semanticscholar.org/d827/32de6336dd6443ff33cccbb92ced0196ecc1.pdf",
        "name": "CSE",
        "code": [
            {
                "language": "Theano",
                "link": "https://github.com/XiaoqiJiao/COLING2018"
            }
        ],
        "s2_paper_id": "d82732de6336dd6443ff33cccbb92ced0196ecc1"
    },
    {
        "paper_title": "Incremental Domain Adaptation for Neural Machine Translation in Low-Resource Settings",
        "paper_link": "https://www.aclweb.org/anthology/W19-4601",
        "name": "AraSIF",
        "code": [
            {
                "language": "Python",
                "link": "https://github.com/DFKI-Interactive-Machine-Learning/AraSIF"
            }
        ]
    }
]