<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tu-etal-2023-ssp">
    <titleInfo>
        <title>SSP: Self-Supervised Post-training for Conversational Search</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Quan</namePart>
        <namePart type="family">Tu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shen</namePart>
        <namePart type="family">Gao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaolong</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhao</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ji-Rong</namePart>
        <namePart type="family">Wen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rui</namePart>
        <namePart type="family">Yan</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>Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which usually initialize parameters by query reformulation to discover contextualized dependency, have trouble in understanding the dialogue structure information and struggle with contextual semantic vanishing. In this paper, we propose pasted macro ‘FULLMODEL’ (pasted macro ‘MODEL’) which is a new post-training paradigm with three self-supervised tasks to efficiently initialize the conversational search model to enhance the dialogue structure and contextual semantic understanding. Furthermore, the pasted macro ‘MODEL’ can be plugged into most of the existing conversational models to boost their performance. To verify the effectiveness of our proposed method, we apply the conversational encoder post-trained by pasted macro ‘MODEL’ on the conversational search task using two benchmark datasets: CAsT-19 and CAsT-20.Extensive experiments that our pasted macro ‘MODEL’ can boost the performance of several existing conversational search methods. Our source code is available at https://github.com/morecry/SSP.</abstract>
    <identifier type="citekey">tu-etal-2023-ssp</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.837</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.837</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>13237</start>
            <end>13249</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SSP: Self-Supervised Post-training for Conversational Search
%A Tu, Quan
%A Gao, Shen
%A Wu, Xiaolong
%A Cao, Zhao
%A Wen, Ji-Rong
%A Yan, Rui
%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 tu-etal-2023-ssp
%X Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which usually initialize parameters by query reformulation to discover contextualized dependency, have trouble in understanding the dialogue structure information and struggle with contextual semantic vanishing. In this paper, we propose pasted macro ‘FULLMODEL’ (pasted macro ‘MODEL’) which is a new post-training paradigm with three self-supervised tasks to efficiently initialize the conversational search model to enhance the dialogue structure and contextual semantic understanding. Furthermore, the pasted macro ‘MODEL’ can be plugged into most of the existing conversational models to boost their performance. To verify the effectiveness of our proposed method, we apply the conversational encoder post-trained by pasted macro ‘MODEL’ on the conversational search task using two benchmark datasets: CAsT-19 and CAsT-20.Extensive experiments that our pasted macro ‘MODEL’ can boost the performance of several existing conversational search methods. Our source code is available at https://github.com/morecry/SSP.
%R 10.18653/v1/2023.findings-acl.837
%U https://aclanthology.org/2023.findings-acl.837
%U https://doi.org/10.18653/v1/2023.findings-acl.837
%P 13237-13249

Markdown (Informal)

[SSP: Self-Supervised Post-training for Conversational Search](https://aclanthology.org/2023.findings-acl.837) (Tu et al., Findings 2023)

• SSP: Self-Supervised Post-training for Conversational Search (Tu et al., Findings 2023)

ACL

• Quan Tu, Shen Gao, Xiaolong Wu, Zhao Cao, Ji-Rong Wen, and Rui Yan. 2023. SSP: Self-Supervised Post-training for Conversational Search. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13237–13249, Toronto, Canada. Association for Computational Linguistics.