<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sung-etal-2023-optimizing">
    <titleInfo>
        <title>Optimizing Test-Time Query Representations for Dense Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mujeen</namePart>
        <namePart type="family">Sung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jungsoo</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaewoo</namePart>
        <namePart type="family">Kang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Danqi</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinhyuk</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent developments of dense retrieval rely on quality representations of queries and contexts from pre-trained query and context encoders. In this paper, we introduce TOUR (Test-Time Optimization of Query Representations), which further optimizes instance-level query representations guided by signals from test-time retrieval results. We leverage a cross-encoder re-ranker to provide fine-grained pseudo labels over retrieval results and iteratively optimize query representations with gradient descent. Our theoretical analysis reveals that TOUR can be viewed as a generalization of the classical Rocchio algorithm for pseudo relevance feedback, and we present two variants that leverage pseudo-labels as hard binary or soft continuous labels. We first apply TOUR on phrase retrieval with our proposed phrase re-ranker, and also evaluate its effectiveness on passage retrieval with an off-the-shelf re-ranker. TOUR greatly improves end-to-end open-domain question answering accuracy, as well as passage retrieval performance. TOUR also consistently improves direct re-ranking by up to 2.0% while running 1.3–2.4x faster with an efficient implementation.</abstract>
    <identifier type="citekey">sung-etal-2023-optimizing</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.354</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.354</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>5731</start>
            <end>5746</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Optimizing Test-Time Query Representations for Dense Retrieval
%A Sung, Mujeen
%A Park, Jungsoo
%A Kang, Jaewoo
%A Chen, Danqi
%A Lee, Jinhyuk
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F sung-etal-2023-optimizing
%X Recent developments of dense retrieval rely on quality representations of queries and contexts from pre-trained query and context encoders. In this paper, we introduce TOUR (Test-Time Optimization of Query Representations), which further optimizes instance-level query representations guided by signals from test-time retrieval results. We leverage a cross-encoder re-ranker to provide fine-grained pseudo labels over retrieval results and iteratively optimize query representations with gradient descent. Our theoretical analysis reveals that TOUR can be viewed as a generalization of the classical Rocchio algorithm for pseudo relevance feedback, and we present two variants that leverage pseudo-labels as hard binary or soft continuous labels. We first apply TOUR on phrase retrieval with our proposed phrase re-ranker, and also evaluate its effectiveness on passage retrieval with an off-the-shelf re-ranker. TOUR greatly improves end-to-end open-domain question answering accuracy, as well as passage retrieval performance. TOUR also consistently improves direct re-ranking by up to 2.0% while running 1.3–2.4x faster with an efficient implementation.
%R 10.18653/v1/2023.findings-acl.354
%U https://aclanthology.org/2023.findings-acl.354
%U https://doi.org/10.18653/v1/2023.findings-acl.354
%P 5731-5746

Markdown (Informal)

[Optimizing Test-Time Query Representations for Dense Retrieval](https://aclanthology.org/2023.findings-acl.354) (Sung et al., Findings 2023)

• Optimizing Test-Time Query Representations for Dense Retrieval (Sung et al., Findings 2023)

ACL

• Mujeen Sung, Jungsoo Park, Jaewoo Kang, Danqi Chen, and Jinhyuk Lee. 2023. Optimizing Test-Time Query Representations for Dense Retrieval. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5731–5746, Toronto, Canada. Association for Computational Linguistics.