<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-mitigating">
    <titleInfo>
        <title>Mitigating Contradictions in Dialogue Based on Contrastive Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weizhao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junsheng</namePart>
        <namePart type="family">Kong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ben</namePart>
        <namePart type="family">Liao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Cai</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>Chatbot models have achieved remarkable progress in recent years but tend to yield contradictory responses. In this paper, we exploit the advantage of contrastive learning technique to mitigate this issue. To endow the model with the ability of discriminating contradictory patterns, we minimize the similarity between the target response and contradiction related negative example. The negative example is generated with learnable latent noise, which receives contradiction related feedback from the pretrained critic. Experimental results show that our method helps to avoid contradictions in response generation while preserving response fluency, outperforming existing methods on both automatic and human evaluation.</abstract>
    <identifier type="citekey">li-etal-2022-mitigating</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-acl.219</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-acl.219</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>2781</start>
            <end>2788</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Mitigating Contradictions in Dialogue Based on Contrastive Learning
%A Li, Weizhao
%A Kong, Junsheng
%A Liao, Ben
%A Cai, Yi
%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 li-etal-2022-mitigating
%X Chatbot models have achieved remarkable progress in recent years but tend to yield contradictory responses. In this paper, we exploit the advantage of contrastive learning technique to mitigate this issue. To endow the model with the ability of discriminating contradictory patterns, we minimize the similarity between the target response and contradiction related negative example. The negative example is generated with learnable latent noise, which receives contradiction related feedback from the pretrained critic. Experimental results show that our method helps to avoid contradictions in response generation while preserving response fluency, outperforming existing methods on both automatic and human evaluation.
%R 10.18653/v1/2022.findings-acl.219
%U https://aclanthology.org/2022.findings-acl.219
%U https://doi.org/10.18653/v1/2022.findings-acl.219
%P 2781-2788

Markdown (Informal)

[Mitigating Contradictions in Dialogue Based on Contrastive Learning](https://aclanthology.org/2022.findings-acl.219) (Li et al., Findings 2022)

• Mitigating Contradictions in Dialogue Based on Contrastive Learning (Li et al., Findings 2022)

ACL

• Weizhao Li, Junsheng Kong, Ben Liao, and Yi Cai. 2022. Mitigating Contradictions in Dialogue Based on Contrastive Learning. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2781–2788, Dublin, Ireland. Association for Computational Linguistics.