@inproceedings{chen-etal-2023-augmenting,
title = "Augmenting Pre-trained Language Models with {QA}-Memory for Open-Domain Question Answering",
author = "Chen, Wenhu and
Verga, Pat and
de Jong, Michiel and
Wieting, John and
Cohen, William W.",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.117",
doi = "10.18653/v1/2023.eacl-main.117",
pages = "1597--1610",
abstract = "Existing state-of-the-art methods for open-domain question-answering (ODQA) use an open book approach in which information is first retrieved from a large text corpus or knowledge base (KB) and then reasoned over to produce an answer. A recent alternative is to retrieve from a collection of previously-generated question-answer pairs; this has several practical advantages including being more memory and compute-efficient. Question-answer pairs are also appealing in that they can be viewed as an intermediate between text and KB triples: like KB triples, they often concisely express a single relationship, but like text, have much higher coverage than traditional KBs. In this work, we describe a new QA system that augments a text-to-text model with a large memory of question-answer pairs, and a new pre-training task for the latent step of question retrieval. The pre-training task substantially simplifies training and greatly improves performance on smaller QA benchmarks. Unlike prior systems of this sort, our QA system can also answer multi-hop questions that do not explicitly appear in the collection of stored question-answer pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-augmenting">
<titleInfo>
<title>Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pat</namePart>
<namePart type="family">Verga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michiel</namePart>
<namePart type="family">de Jong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Wieting</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing state-of-the-art methods for open-domain question-answering (ODQA) use an open book approach in which information is first retrieved from a large text corpus or knowledge base (KB) and then reasoned over to produce an answer. A recent alternative is to retrieve from a collection of previously-generated question-answer pairs; this has several practical advantages including being more memory and compute-efficient. Question-answer pairs are also appealing in that they can be viewed as an intermediate between text and KB triples: like KB triples, they often concisely express a single relationship, but like text, have much higher coverage than traditional KBs. In this work, we describe a new QA system that augments a text-to-text model with a large memory of question-answer pairs, and a new pre-training task for the latent step of question retrieval. The pre-training task substantially simplifies training and greatly improves performance on smaller QA benchmarks. Unlike prior systems of this sort, our QA system can also answer multi-hop questions that do not explicitly appear in the collection of stored question-answer pairs.</abstract>
<identifier type="citekey">chen-etal-2023-augmenting</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.117</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.117</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1597</start>
<end>1610</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering
%A Chen, Wenhu
%A Verga, Pat
%A de Jong, Michiel
%A Wieting, John
%A Cohen, William W.
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F chen-etal-2023-augmenting
%X Existing state-of-the-art methods for open-domain question-answering (ODQA) use an open book approach in which information is first retrieved from a large text corpus or knowledge base (KB) and then reasoned over to produce an answer. A recent alternative is to retrieve from a collection of previously-generated question-answer pairs; this has several practical advantages including being more memory and compute-efficient. Question-answer pairs are also appealing in that they can be viewed as an intermediate between text and KB triples: like KB triples, they often concisely express a single relationship, but like text, have much higher coverage than traditional KBs. In this work, we describe a new QA system that augments a text-to-text model with a large memory of question-answer pairs, and a new pre-training task for the latent step of question retrieval. The pre-training task substantially simplifies training and greatly improves performance on smaller QA benchmarks. Unlike prior systems of this sort, our QA system can also answer multi-hop questions that do not explicitly appear in the collection of stored question-answer pairs.
%R 10.18653/v1/2023.eacl-main.117
%U https://aclanthology.org/2023.eacl-main.117
%U https://doi.org/10.18653/v1/2023.eacl-main.117
%P 1597-1610
Markdown (Informal)
[Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering](https://aclanthology.org/2023.eacl-main.117) (Chen et al., EACL 2023)
ACL