Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix/reranking tutorial typos #1313

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+3 −3
Open

fix/reranking tutorial typos #1313

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions Tutorials/5_Reranking/5.1_Intro.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,11 +11,11 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Reranker is disigned in cross-encoder architecture that takes the query and text at the same time and directly output their score of similarity. It is more capable on scoring the query-text relevance, but with the tradeoff of slower speed. Thus, complete retrieval system usually contains retrievers in the first stage to do a large scope retrieval, and then follows by rerankers to rerank the results more precisely.\n",
"Reranker is designed in cross-encoder architecture that takes the query and text at the same time and directly output their score of similarity. It is more capable of scoring the query-text relevance, but with the tradeoff of slower speed. Thus, a complete retrieval system usually contains retrievers in the first stage to do a large scope retrieval, and then followed by rerankers to rerank the results more precisely.\n",
"\n",
"In this tutorial, we will go through text retrieval pipeline with reranker and evaluate the results before and after reranking.\n",
"\n",
"Note: Step 1-4 are identical to the tutorial of [evaluation](https://github.com/FlagOpen/FlagEmbedding/tree/master/Tutorials/4_Evaluation). We suggest to first go through that if you are not familiar with retrieval."
"Note: Steps 1-4 are identical to the tutorial of [evaluation](https://github.com/FlagOpen/FlagEmbedding/tree/master/Tutorials/4_Evaluation). We suggest to first go through that if you are not familiar with retrieval."
]
},
{
Expand Down Expand Up @@ -317,7 +317,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"For details of these metrics, please checkout the tutorial of [evaluation](https://github.com/FlagOpen/FlagEmbedding/tree/master/Tutorials/4_Evaluation)."
"For details of these metrics, please check out the tutorial of [evaluation](https://github.com/FlagOpen/FlagEmbedding/tree/master/Tutorials/4_Evaluation)."
]
},
{
Expand Down