<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deriu-etal-2022-probing">
    <titleInfo>
        <title>Probing the Robustness of Trained Metrics for Conversational Dialogue Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jan</namePart>
        <namePart type="family">Deriu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Don</namePart>
        <namePart type="family">Tuggener</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pius</namePart>
        <namePart type="family">Von Däniken</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mark</namePart>
        <namePart type="family">Cieliebak</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>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</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>This paper introduces an adversarial method to stress-test trained metrics for the evaluation of conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained metrics. We apply our method to test recently proposed trained metrics. We find that they all are susceptible to giving high scores to responses generated by rather simple and obviously flawed strategies that our method converges on. For instance, simply copying parts of the conversation context to form a response yields competitive scores or even outperforms responses written by humans.</abstract>
    <identifier type="citekey">deriu-etal-2022-probing</identifier>
    <identifier type="doi">10.18653/v1/2022.acl-short.85</identifier>
    <location>
        <url>https://aclanthology.org/2022.acl-short.85</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>750</start>
            <end>761</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Probing the Robustness of Trained Metrics for Conversational Dialogue Systems
%A Deriu, Jan
%A Tuggener, Don
%A Von Däniken, Pius
%A Cieliebak, Mark
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F deriu-etal-2022-probing
%X This paper introduces an adversarial method to stress-test trained metrics for the evaluation of conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained metrics. We apply our method to test recently proposed trained metrics. We find that they all are susceptible to giving high scores to responses generated by rather simple and obviously flawed strategies that our method converges on. For instance, simply copying parts of the conversation context to form a response yields competitive scores or even outperforms responses written by humans.
%R 10.18653/v1/2022.acl-short.85
%U https://aclanthology.org/2022.acl-short.85
%U https://doi.org/10.18653/v1/2022.acl-short.85
%P 750-761

Markdown (Informal)

[Probing the Robustness of Trained Metrics for Conversational Dialogue Systems](https://aclanthology.org/2022.acl-short.85) (Deriu et al., ACL 2022)

• Probing the Robustness of Trained Metrics for Conversational Dialogue Systems (Deriu et al., ACL 2022)

ACL

• Jan Deriu, Don Tuggener, Pius Von Däniken, and Mark Cieliebak. 2022. Probing the Robustness of Trained Metrics for Conversational Dialogue Systems. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 750–761, Dublin, Ireland. Association for Computational Linguistics.