@inproceedings{seonwoo-etal-2022-two,
title = "Two-Step Question Retrieval for Open-Domain {QA}",
author = "Seonwoo, Yeon and
Son, Juhee and
Jin, Jiho and
Lee, Sang-Woo and
Kim, Ji-Hoon and
Ha, Jung-Woo and
Oh, Alice",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.117",
doi = "10.18653/v1/2022.findings-acl.117",
pages = "1487--1492",
abstract = "The retriever-reader pipeline has shown promising performance in open-domain QA but suffers from a very slow inference speed. Recently proposed question retrieval models tackle this problem by indexing question-answer pairs and searching for similar questions. These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models. This paper proposes a two-step question retrieval model, SQuID (Sequential Question-Indexed Dense retrieval) and distant supervision for training. SQuID uses two bi-encoders for question retrieval. The first-step retriever selects top-k similar questions, and the second-step retriever finds the most similar question from the top-k questions. We evaluate the performance and the computational efficiency of SQuID. The results show that SQuID significantly increases the performance of existing question retrieval models with a negligible loss on inference speed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seonwoo-etal-2022-two">
<titleInfo>
<title>Two-Step Question Retrieval for Open-Domain QA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yeon</namePart>
<namePart type="family">Seonwoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juhee</namePart>
<namePart type="family">Son</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiho</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sang-Woo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji-Hoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jung-Woo</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The retriever-reader pipeline has shown promising performance in open-domain QA but suffers from a very slow inference speed. Recently proposed question retrieval models tackle this problem by indexing question-answer pairs and searching for similar questions. These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models. This paper proposes a two-step question retrieval model, SQuID (Sequential Question-Indexed Dense retrieval) and distant supervision for training. SQuID uses two bi-encoders for question retrieval. The first-step retriever selects top-k similar questions, and the second-step retriever finds the most similar question from the top-k questions. We evaluate the performance and the computational efficiency of SQuID. The results show that SQuID significantly increases the performance of existing question retrieval models with a negligible loss on inference speed.</abstract>
<identifier type="citekey">seonwoo-etal-2022-two</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.117</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.117</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1487</start>
<end>1492</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Two-Step Question Retrieval for Open-Domain QA
%A Seonwoo, Yeon
%A Son, Juhee
%A Jin, Jiho
%A Lee, Sang-Woo
%A Kim, Ji-Hoon
%A Ha, Jung-Woo
%A Oh, Alice
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F seonwoo-etal-2022-two
%X The retriever-reader pipeline has shown promising performance in open-domain QA but suffers from a very slow inference speed. Recently proposed question retrieval models tackle this problem by indexing question-answer pairs and searching for similar questions. These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models. This paper proposes a two-step question retrieval model, SQuID (Sequential Question-Indexed Dense retrieval) and distant supervision for training. SQuID uses two bi-encoders for question retrieval. The first-step retriever selects top-k similar questions, and the second-step retriever finds the most similar question from the top-k questions. We evaluate the performance and the computational efficiency of SQuID. The results show that SQuID significantly increases the performance of existing question retrieval models with a negligible loss on inference speed.
%R 10.18653/v1/2022.findings-acl.117
%U https://aclanthology.org/2022.findings-acl.117
%U https://doi.org/10.18653/v1/2022.findings-acl.117
%P 1487-1492
Markdown (Informal)
[Two-Step Question Retrieval for Open-Domain QA](https://aclanthology.org/2022.findings-acl.117) (Seonwoo et al., Findings 2022)
ACL
- Yeon Seonwoo, Juhee Son, Jiho Jin, Sang-Woo Lee, Ji-Hoon Kim, Jung-Woo Ha, and Alice Oh. 2022. Two-Step Question Retrieval for Open-Domain QA. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1487–1492, Dublin, Ireland. Association for Computational Linguistics.