<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-chang-2022-improving">
    <titleInfo>
        <title>Improving Response Diversity through Commonsense-Aware Empathetic Response Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tzu-Hsien</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chia-Hui</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <language>
        <languageTerm type="text">Chinese</languageTerm>
        <languageTerm type="code" authority="iso639-2b">chi</languageTerm>
    </language>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)</title>
        </titleInfo>
        <originInfo>
            <publisher>The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)</publisher>
            <place>
                <placeTerm type="text">Taipei, Taiwan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Due to the lack of conversation practice, the main challenge for the second-language learners is speaking. Our goal is to develop a chatbot to encourage individuals to reflect, describe, analyse and communicate what they read as well as improve students’ English expression skills. In this paper, we exploit COMMET, an inferential commonsense knowledge generator, as the background knowledge to improve the generation diversity. We consider two approaches to increase the diversity of empathetic response generation. For nonpretrained models, We apply AdaLabel (Wang et al., 2021) to Commonsense-aware Empathetic model (Sabour et al., 2022) and improve Distinct-2 score from 2.99 to 4.08 on EMPATHETIC DIALOGUES (ED). Furthermore, we augment the pretrained BART model with various commonsense knowledge to generate more informative empathetic responses. Not only has the automatic evaluation of distinct-2 scores improved from 9.11 to 11.21, but the manual case study also shows that CE-BART significantly outperform CEM-AdaLabel.</abstract>
    <identifier type="citekey">huang-chang-2022-improving</identifier>
    <location>
        <url>https://aclanthology.org/2022.rocling-1.37</url>
    </location>
    <part>
        <date>2022-11</date>
        <extent unit="page">
            <start>299</start>
            <end>306</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Response Diversity through Commonsense-Aware Empathetic Response Generation
%A Huang, Tzu-Hsien
%A Chang, Chia-Hui
%S Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)
%D 2022
%8 November
%I The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
%C Taipei, Taiwan
%G Chinese
%F huang-chang-2022-improving
%X Due to the lack of conversation practice, the main challenge for the second-language learners is speaking. Our goal is to develop a chatbot to encourage individuals to reflect, describe, analyse and communicate what they read as well as improve students’ English expression skills. In this paper, we exploit COMMET, an inferential commonsense knowledge generator, as the background knowledge to improve the generation diversity. We consider two approaches to increase the diversity of empathetic response generation. For nonpretrained models, We apply AdaLabel (Wang et al., 2021) to Commonsense-aware Empathetic model (Sabour et al., 2022) and improve Distinct-2 score from 2.99 to 4.08 on EMPATHETIC DIALOGUES (ED). Furthermore, we augment the pretrained BART model with various commonsense knowledge to generate more informative empathetic responses. Not only has the automatic evaluation of distinct-2 scores improved from 9.11 to 11.21, but the manual case study also shows that CE-BART significantly outperform CEM-AdaLabel.
%U https://aclanthology.org/2022.rocling-1.37
%P 299-306

Markdown (Informal)

[Improving Response Diversity through Commonsense-Aware Empathetic Response Generation](https://aclanthology.org/2022.rocling-1.37) (Huang & Chang, ROCLING 2022)

• Improving Response Diversity through Commonsense-Aware Empathetic Response Generation (Huang & Chang, ROCLING 2022)

ACL

• Tzu-Hsien Huang and Chia-Hui Chang. 2022. Improving Response Diversity through Commonsense-Aware Empathetic Response Generation. In Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022), pages 299–306, Taipei, Taiwan. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP).