@inproceedings{sato-etal-2022-bipartite,
title = "Bipartite-play Dialogue Collection for Practical Automatic Evaluation of Dialogue Systems",
author = "Sato, Shiki and
Kishinami, Yosuke and
Sugiyama, Hiroaki and
Akama, Reina and
Tokuhisa, Ryoko and
Suzuki, Jun",
editor = "Hanqi, Yan and
Zonghan, Yang and
Ruder, Sebastian and
Xiaojun, Wan",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: Student Research Workshop",
month = nov,
year = "2022",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-srw.2",
doi = "10.18653/v1/2022.aacl-srw.2",
pages = "8--16",
abstract = "Automation of dialogue system evaluation is a driving force for the efficient development of dialogue systems. This paper introduces the bipartite-play method, a dialogue collection method for automating dialogue system evaluation. It addresses the limitations of existing dialogue collection methods: (i) inability to compare with systems that are not publicly available, and (ii) vulnerability to cheating by intentionally selecting systems to be compared. Experimental results show that the automatic evaluation using the bipartite-play method mitigates these two drawbacks and correlates as strongly with human subjectivity as existing methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sato-etal-2022-bipartite">
<titleInfo>
<title>Bipartite-play Dialogue Collection for Practical Automatic Evaluation of Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shiki</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yosuke</namePart>
<namePart type="family">Kishinami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Sugiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reina</namePart>
<namePart type="family">Akama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryoko</namePart>
<namePart type="family">Tokuhisa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Hanqi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zonghan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wan</namePart>
<namePart type="family">Xiaojun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automation of dialogue system evaluation is a driving force for the efficient development of dialogue systems. This paper introduces the bipartite-play method, a dialogue collection method for automating dialogue system evaluation. It addresses the limitations of existing dialogue collection methods: (i) inability to compare with systems that are not publicly available, and (ii) vulnerability to cheating by intentionally selecting systems to be compared. Experimental results show that the automatic evaluation using the bipartite-play method mitigates these two drawbacks and correlates as strongly with human subjectivity as existing methods.</abstract>
<identifier type="citekey">sato-etal-2022-bipartite</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-srw.2</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-srw.2</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>8</start>
<end>16</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bipartite-play Dialogue Collection for Practical Automatic Evaluation of Dialogue Systems
%A Sato, Shiki
%A Kishinami, Yosuke
%A Sugiyama, Hiroaki
%A Akama, Reina
%A Tokuhisa, Ryoko
%A Suzuki, Jun
%Y Hanqi, Yan
%Y Zonghan, Yang
%Y Ruder, Sebastian
%Y Xiaojun, Wan
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: Student Research Workshop
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online
%F sato-etal-2022-bipartite
%X Automation of dialogue system evaluation is a driving force for the efficient development of dialogue systems. This paper introduces the bipartite-play method, a dialogue collection method for automating dialogue system evaluation. It addresses the limitations of existing dialogue collection methods: (i) inability to compare with systems that are not publicly available, and (ii) vulnerability to cheating by intentionally selecting systems to be compared. Experimental results show that the automatic evaluation using the bipartite-play method mitigates these two drawbacks and correlates as strongly with human subjectivity as existing methods.
%R 10.18653/v1/2022.aacl-srw.2
%U https://aclanthology.org/2022.aacl-srw.2
%U https://doi.org/10.18653/v1/2022.aacl-srw.2
%P 8-16
Markdown (Informal)
[Bipartite-play Dialogue Collection for Practical Automatic Evaluation of Dialogue Systems](https://aclanthology.org/2022.aacl-srw.2) (Sato et al., AACL-IJCNLP 2022)
ACL
- Shiki Sato, Yosuke Kishinami, Hiroaki Sugiyama, Reina Akama, Ryoko Tokuhisa, and Jun Suzuki. 2022. Bipartite-play Dialogue Collection for Practical Automatic Evaluation of Dialogue Systems. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 8–16, Online. Association for Computational Linguistics.