<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2022-measuring">
    <titleInfo>
        <title>Measuring and Improving Semantic Diversity of Dialogue Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Seungju</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Beomsu</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Buru</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Response diversity has become an important criterion for evaluating the quality of open-domain dialogue generation models. However, current evaluation metrics for response diversity often fail to capture the semantic diversity of generated responses, as they mainly consider lexical aspects of the generated responses. In this paper, we introduce a new automatic evaluation metric to measure the semantic diversity of generated responses. Through human evaluation, we demonstrate that our proposed metric captures human judgments on response diversity better than existing lexical-level diversity metrics. Furthermore, motivated by analyzing an existing dialogue dataset, we propose a simple yet effective learning method that improves the semantic diversity of generated responses. Our learning method weights training samples based on the semantic distribution of the training set. We show that our learning method improves response diversity and coherency better than other baseline methods through automatic and human evaluation.</abstract>
    <identifier type="citekey">han-etal-2022-measuring</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.66</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.66</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>934</start>
            <end>950</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Measuring and Improving Semantic Diversity of Dialogue Generation
%A Han, Seungju
%A Kim, Beomsu
%A Chang, Buru
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F han-etal-2022-measuring
%X Response diversity has become an important criterion for evaluating the quality of open-domain dialogue generation models. However, current evaluation metrics for response diversity often fail to capture the semantic diversity of generated responses, as they mainly consider lexical aspects of the generated responses. In this paper, we introduce a new automatic evaluation metric to measure the semantic diversity of generated responses. Through human evaluation, we demonstrate that our proposed metric captures human judgments on response diversity better than existing lexical-level diversity metrics. Furthermore, motivated by analyzing an existing dialogue dataset, we propose a simple yet effective learning method that improves the semantic diversity of generated responses. Our learning method weights training samples based on the semantic distribution of the training set. We show that our learning method improves response diversity and coherency better than other baseline methods through automatic and human evaluation.
%R 10.18653/v1/2022.findings-emnlp.66
%U https://aclanthology.org/2022.findings-emnlp.66
%U https://doi.org/10.18653/v1/2022.findings-emnlp.66
%P 934-950

Markdown (Informal)

[Measuring and Improving Semantic Diversity of Dialogue Generation](https://aclanthology.org/2022.findings-emnlp.66) (Han et al., Findings 2022)

• Measuring and Improving Semantic Diversity of Dialogue Generation (Han et al., Findings 2022)

ACL

• Seungju Han, Beomsu Kim, and Buru Chang. 2022. Measuring and Improving Semantic Diversity of Dialogue Generation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 934–950, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.