Latent Retrieval for Weakly Supervised Open Domain Question Answering

06/01/2019
by   Kenton Lee, et al.
0

Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. We argue that both are suboptimal, since gold evidence is not always available, and QA is fundamentally different from IR. We show for the first time that it is possible to jointly learn the retriever and reader from question-answer string pairs and without any IR system. In this setting, evidence retrieval from all of Wikipedia is treated as a latent variable. Since this is impractical to learn from scratch, we pre-train the retriever with an Inverse Cloze Task. We evaluate on open versions of five QA datasets. On datasets where the questioner already knows the answer, a traditional IR system such as BM25 is sufficient. On datasets where a user is genuinely seeking an answer, we show that learned retrieval is crucial, outperforming BM25 by up to 19 points in exact match.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/17/2019

Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

Multi-hop question answering (QA) requires an information retrieval (IR)...
research
03/03/2021

Weakly-Supervised Open-Retrieval Conversational Question Answering

Recent studies on Question Answering (QA) and Conversational QA (ConvQA)...
research
09/22/2020

Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering

Evidence retrieval is a key component of explainable question answering ...
research
09/17/2019

Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering

A key challenge of multi-hop question answering (QA) in the open-domain ...
research
07/20/2020

Frustratingly Hard Evidence Retrieval for QA Over Books

A lot of progress has been made to improve question answering (QA) in re...
research
05/04/2020

DoQA – Accessing Domain-Specific FAQs via Conversational QA

The goal of this work is to build conversational Question Answering (QA)...
research
09/11/2019

A Discrete Hard EM Approach for Weakly Supervised Question Answering

Many question answering (QA) tasks only provide weak supervision for how...

Please sign up or login with your details

Forgot password? Click here to reset