@inproceedings{yoshikoshi-etal-2022-explicit,
title = "Explicit Use of Topicality in Dialogue Response Generation",
author = "Yoshikoshi, Takumi and
Atarashi, Hayato and
Kodama, Takashi and
Kurohashi, Sadao",
editor = "Ippolito, Daphne and
Li, Liunian Harold and
Pacheco, Maria Leonor and
Chen, Danqi and
Xue, Nianwen",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-srw.28",
doi = "10.18653/v1/2022.naacl-srw.28",
pages = "222--228",
abstract = "The current chat dialogue systems implicitly consider the topic given the context, but not explicitly. As a result, these systems often generate inconsistent responses with the topic of the moment. In this study, we propose a dialogue system that responds appropriately following the topic by selecting the entity with the highest {``}topicality.{''} In topicality estimation, the model is trained through self-supervised learning that regards entities that appear in both context and response as the topic entities. In response generation, the model is trained to generate topic-relevant responses based on the estimated topicality. Experimental results show that our proposed system can follow the topic more than the existing dialogue system that considers only the context.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoshikoshi-etal-2022-explicit">
<titleInfo>
<title>Explicit Use of Topicality in Dialogue Response Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takumi</namePart>
<namePart type="family">Yoshikoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hayato</namePart>
<namePart type="family">Atarashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Kodama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daphne</namePart>
<namePart type="family">Ippolito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liunian</namePart>
<namePart type="given">Harold</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Leonor</namePart>
<namePart type="family">Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The current chat dialogue systems implicitly consider the topic given the context, but not explicitly. As a result, these systems often generate inconsistent responses with the topic of the moment. In this study, we propose a dialogue system that responds appropriately following the topic by selecting the entity with the highest “topicality.” In topicality estimation, the model is trained through self-supervised learning that regards entities that appear in both context and response as the topic entities. In response generation, the model is trained to generate topic-relevant responses based on the estimated topicality. Experimental results show that our proposed system can follow the topic more than the existing dialogue system that considers only the context.</abstract>
<identifier type="citekey">yoshikoshi-etal-2022-explicit</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-srw.28</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-srw.28</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>222</start>
<end>228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Explicit Use of Topicality in Dialogue Response Generation
%A Yoshikoshi, Takumi
%A Atarashi, Hayato
%A Kodama, Takashi
%A Kurohashi, Sadao
%Y Ippolito, Daphne
%Y Li, Liunian Harold
%Y Pacheco, Maria Leonor
%Y Chen, Danqi
%Y Xue, Nianwen
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F yoshikoshi-etal-2022-explicit
%X The current chat dialogue systems implicitly consider the topic given the context, but not explicitly. As a result, these systems often generate inconsistent responses with the topic of the moment. In this study, we propose a dialogue system that responds appropriately following the topic by selecting the entity with the highest “topicality.” In topicality estimation, the model is trained through self-supervised learning that regards entities that appear in both context and response as the topic entities. In response generation, the model is trained to generate topic-relevant responses based on the estimated topicality. Experimental results show that our proposed system can follow the topic more than the existing dialogue system that considers only the context.
%R 10.18653/v1/2022.naacl-srw.28
%U https://aclanthology.org/2022.naacl-srw.28
%U https://doi.org/10.18653/v1/2022.naacl-srw.28
%P 222-228
Markdown (Informal)
[Explicit Use of Topicality in Dialogue Response Generation](https://aclanthology.org/2022.naacl-srw.28) (Yoshikoshi et al., NAACL 2022)
ACL
- Takumi Yoshikoshi, Hayato Atarashi, Takashi Kodama, and Sadao Kurohashi. 2022. Explicit Use of Topicality in Dialogue Response Generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop, pages 222–228, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.