<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2023-density">
    <titleInfo>
        <title>DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">ChaeHun</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seungil</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Rim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaegul</namePart>
        <namePart type="family">Choo</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>Despite the recent advances in open-domain dialogue systems, building a reliable evaluation metric is still a challenging problem. Recent studies proposed learnable metrics based on classification models trained to distinguish the correct response. However, neural classifiers are known to make overly confident predictions for examples from unseen distributions. We propose DENSITY, which evaluates a response by utilizing density estimation on the feature space derived from a neural classifier. Our metric measures how likely a response would appear in the distribution of human conversations. Moreover, to improve the performance of DENSITY, we utilize contrastive learning to further compress the feature space. Experiments on multiple response evaluation datasets show that DENSITY correlates better with human evaluations than the existing metrics.</abstract>
    <identifier type="citekey">park-etal-2023-density</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.896</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.896/</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>14222</start>
            <end>14236</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation
%A Park, ChaeHun
%A Lee, Seungil
%A Rim, Daniel
%A Choo, Jaegul
%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 park-etal-2023-density
%X Despite the recent advances in open-domain dialogue systems, building a reliable evaluation metric is still a challenging problem. Recent studies proposed learnable metrics based on classification models trained to distinguish the correct response. However, neural classifiers are known to make overly confident predictions for examples from unseen distributions. We propose DENSITY, which evaluates a response by utilizing density estimation on the feature space derived from a neural classifier. Our metric measures how likely a response would appear in the distribution of human conversations. Moreover, to improve the performance of DENSITY, we utilize contrastive learning to further compress the feature space. Experiments on multiple response evaluation datasets show that DENSITY correlates better with human evaluations than the existing metrics.
%R 10.18653/v1/2023.findings-acl.896
%U https://aclanthology.org/2023.findings-acl.896/
%U https://doi.org/10.18653/v1/2023.findings-acl.896
%P 14222-14236

Markdown (Informal)

[DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation](https://aclanthology.org/2023.findings-acl.896/) (Park et al., Findings 2023)

• DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation (Park et al., Findings 2023)

ACL

• ChaeHun Park, Seungil Lee, Daniel Rim, and Jaegul Choo. 2023. DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 14222–14236, Toronto, Canada. Association for Computational Linguistics.