From 0f16dd0ac284b1ca012949b87f7d760feb3e1d59 Mon Sep 17 00:00:00 2001
From: Quentin Lhoest <42851186+lhoestq@users.noreply.github.com>
Date: Tue, 25 Aug 2020 09:57:28 +0200
Subject: [PATCH] Add DPR to models summary (#6690)

* add dpr to models summary

* minor

* minor

* Update docs/source/model_summary.rst

qa -> question answering

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update docs/source/model_summary.rst

qa -> question ansering (cont'd)

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
---
 docs/source/model_summary.rst | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/docs/source/model_summary.rst b/docs/source/model_summary.rst
index 4a675c797a..9ddf38f7b6 100644
--- a/docs/source/model_summary.rst
+++ b/docs/source/model_summary.rst
@@ -14,6 +14,7 @@ Each one of the models in the library falls into one of the following categories
   * :ref:`autoencoding-models`
   * :ref:`seq-to-seq-models`
   * :ref:`multimodal-models`
+  * :ref:`retrieval-based-models`
 
 Autoregressive models are pretrained on the classic language modeling task: guess the next token having read all the
 previous ones. They correspond to the decoder of the original transformer model, and a mask is used on top of the full
@@ -605,6 +606,40 @@ The pretrained model only works for classification.
     More information in this :doc:`model documentation </model_doc/mmbt.html>`.
     TODO: write this page
 
+.. _retrieval-based-models:
+
+Retrieval-based models
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Some models use documents retrieval during (pre)training and inference for open-domain question answering, for example.
+
+
+DPR
+----------------------------------------------
+
+.. raw:: html
+
+   <a href="https://huggingface.co/models?filter=dpr">
+       <img alt="Models" src="https://img.shields.io/badge/All_model_pages-dpr-blueviolet">
+   </a>
+   <a href="model_doc/ctrl.dpr">
+       <img alt="Doc" src="https://img.shields.io/badge/Model_documentation-dpr-blueviolet">
+   </a>
+
+`Dense Passage Retrieval for Open-Domain Question Answering <https://arxiv.org/abs/2004.04906>`_,
+Vladimir Karpukhin et al.
+
+Dense Passage Retrieval (DPR) - is a set of tools and models for state-of-the-art open-domain question-answering research.
+
+
+DPR consists in three models:
+
+  * Question encoder: encode questions as vectors
+  * Context encoder: encode contexts as vectors
+  * Reader: extract the answer of the questions inside retrieved contexts, along with a relevance score (high if the inferred span actually answers the question).
+
+DPR's pipeline (not implemented yet) uses a retrieval step to find the top k contexts given a certain question, and then it calls the reader with the question and the retrieved documents to get the answer.
+
 More technical aspects
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^