@inproceedings{yang-etal-2022-chatmatch,
title = "{C}hat{M}atch: Evaluating Chatbots by Autonomous Chat Tournaments",
author = "Yang, Ruolan and
Li, Zitong and
Tang, Haifeng and
Zhu, Kenny",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.522",
doi = "10.18653/v1/2022.acl-long.522",
pages = "7579--7590",
abstract = "Existing automatic evaluation systems of chatbots mostly rely on static chat scripts as ground truth, which is hard to obtain, and requires access to the models of the bots as a form of {``}white-box testing{''}. Interactive evaluation mitigates this problem but requires human involvement. In our work, we propose an interactive chatbot evaluation framework in which chatbots compete with each other like in a sports tournament, using flexible scoring metrics. This framework can efficiently rank chatbots independently from their model architectures and the domains for which they are trained.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2022-chatmatch">
<titleInfo>
<title>ChatMatch: Evaluating Chatbots by Autonomous Chat Tournaments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruolan</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zitong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenny</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing automatic evaluation systems of chatbots mostly rely on static chat scripts as ground truth, which is hard to obtain, and requires access to the models of the bots as a form of “white-box testing”. Interactive evaluation mitigates this problem but requires human involvement. In our work, we propose an interactive chatbot evaluation framework in which chatbots compete with each other like in a sports tournament, using flexible scoring metrics. This framework can efficiently rank chatbots independently from their model architectures and the domains for which they are trained.</abstract>
<identifier type="citekey">yang-etal-2022-chatmatch</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.522</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.522</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>7579</start>
<end>7590</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChatMatch: Evaluating Chatbots by Autonomous Chat Tournaments
%A Yang, Ruolan
%A Li, Zitong
%A Tang, Haifeng
%A Zhu, Kenny
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F yang-etal-2022-chatmatch
%X Existing automatic evaluation systems of chatbots mostly rely on static chat scripts as ground truth, which is hard to obtain, and requires access to the models of the bots as a form of “white-box testing”. Interactive evaluation mitigates this problem but requires human involvement. In our work, we propose an interactive chatbot evaluation framework in which chatbots compete with each other like in a sports tournament, using flexible scoring metrics. This framework can efficiently rank chatbots independently from their model architectures and the domains for which they are trained.
%R 10.18653/v1/2022.acl-long.522
%U https://aclanthology.org/2022.acl-long.522
%U https://doi.org/10.18653/v1/2022.acl-long.522
%P 7579-7590
Markdown (Informal)
[ChatMatch: Evaluating Chatbots by Autonomous Chat Tournaments](https://aclanthology.org/2022.acl-long.522) (Yang et al., ACL 2022)
ACL
- Ruolan Yang, Zitong Li, Haifeng Tang, and Kenny Zhu. 2022. ChatMatch: Evaluating Chatbots by Autonomous Chat Tournaments. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7579–7590, Dublin, Ireland. Association for Computational Linguistics.