@article{wang-etal-2024-retrieve,
title = "Retrieve What You Need: A Mutual Learning Framework for Open-domain Question Answering",
author = "Wang, Dingmin and
Huang, Qiuyuan and
Jackson, Matthew and
Gao, Jianfeng",
journal = "Transactions of the Association for Computational Linguistics",
volume = "12",
year = "2024",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2024.tacl-1.14",
doi = "10.1162/tacl_a_00646",
pages = "247--263",
abstract = "An open-domain question answering (QA) system usually follows a retrieve-then-read paradigm, in which a retriever is used to retrieve relevant passages from a large corpus, and then a reader generates answers based on the retrieved passages and the original question. In this paper, we propose a simple and novel mutual learning framework to improve the performance of retrieve-then-read-style models via an intermediate module named the knowledge selector, which we train with reinforcement learning. The key benefits of our proposed intermediate module are: 1) no requirement for additional annotated question-passage pairs; 2) improvements in both retrieval and QA performance, as well as computational efficiency, compared to prior competitive retrieve-then-read models; 3) with no finetuning, improvement in the zero-shot performance of large-scale pre-trained language models, e.g., ChatGPT, by encapsulating the input with relevant knowledge without violating the input length constraint.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-retrieve">
<titleInfo>
<title>Retrieve What You Need: A Mutual Learning Framework for Open-domain Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dingmin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiuyuan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Jackson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>An open-domain question answering (QA) system usually follows a retrieve-then-read paradigm, in which a retriever is used to retrieve relevant passages from a large corpus, and then a reader generates answers based on the retrieved passages and the original question. In this paper, we propose a simple and novel mutual learning framework to improve the performance of retrieve-then-read-style models via an intermediate module named the knowledge selector, which we train with reinforcement learning. The key benefits of our proposed intermediate module are: 1) no requirement for additional annotated question-passage pairs; 2) improvements in both retrieval and QA performance, as well as computational efficiency, compared to prior competitive retrieve-then-read models; 3) with no finetuning, improvement in the zero-shot performance of large-scale pre-trained language models, e.g., ChatGPT, by encapsulating the input with relevant knowledge without violating the input length constraint.</abstract>
<identifier type="citekey">wang-etal-2024-retrieve</identifier>
<identifier type="doi">10.1162/tacl_a_00646</identifier>
<location>
<url>https://aclanthology.org/2024.tacl-1.14</url>
</location>
<part>
<date>2024</date>
<detail type="volume"><number>12</number></detail>
<extent unit="page">
<start>247</start>
<end>263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Retrieve What You Need: A Mutual Learning Framework for Open-domain Question Answering
%A Wang, Dingmin
%A Huang, Qiuyuan
%A Jackson, Matthew
%A Gao, Jianfeng
%J Transactions of the Association for Computational Linguistics
%D 2024
%V 12
%I MIT Press
%C Cambridge, MA
%F wang-etal-2024-retrieve
%X An open-domain question answering (QA) system usually follows a retrieve-then-read paradigm, in which a retriever is used to retrieve relevant passages from a large corpus, and then a reader generates answers based on the retrieved passages and the original question. In this paper, we propose a simple and novel mutual learning framework to improve the performance of retrieve-then-read-style models via an intermediate module named the knowledge selector, which we train with reinforcement learning. The key benefits of our proposed intermediate module are: 1) no requirement for additional annotated question-passage pairs; 2) improvements in both retrieval and QA performance, as well as computational efficiency, compared to prior competitive retrieve-then-read models; 3) with no finetuning, improvement in the zero-shot performance of large-scale pre-trained language models, e.g., ChatGPT, by encapsulating the input with relevant knowledge without violating the input length constraint.
%R 10.1162/tacl_a_00646
%U https://aclanthology.org/2024.tacl-1.14
%U https://doi.org/10.1162/tacl_a_00646
%P 247-263
Markdown (Informal)
[Retrieve What You Need: A Mutual Learning Framework for Open-domain Question Answering](https://aclanthology.org/2024.tacl-1.14) (Wang et al., TACL 2024)
ACL