@inproceedings{rodriguez-cantelar-etal-2023-overview,
title = "Overview of Robust and Multilingual Automatic Evaluation Metricsfor Open-Domain Dialogue Systems at {DSTC} 11 Track 4",
author = "Rodr{\'\i}guez-Cantelar, Mario and
Zhang, Chen and
Tang, Chengguang and
Shi, Ke and
Ghazarian, Sarik and
Sedoc, Jo{\~a}o and
Fernando D{'}Haro, Luis and
Rudnicky, Alexander I.",
editor = "Chen, Yun-Nung and
Crook, Paul and
Galley, Michel and
Ghazarian, Sarik and
Gunasekara, Chulaka and
Gupta, Raghav and
Hedayatnia, Behnam and
Kottur, Satwik and
Moon, Seungwhan and
Zhang, Chen",
booktitle = "Proceedings of The Eleventh Dialog System Technology Challenge",
month = sep,
year = "2023",
address = "Prague, Czech Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.dstc-1.28",
pages = "260--273",
abstract = "The advent and fast development of neural networks have revolutionized the research on dialogue systems and subsequently have triggered various challenges regarding their automatic evaluation. Automatic evaluation of open-domain dialogue systems as an open challenge has been the center of the attention of many researchers. Despite the consistent efforts to improve automatic metrics{'} correlations with human evaluation, there have been very few attempts to assess their robustness over multiple domains and dimensions. Also, their focus is mainly on the English language. All of these challenges prompt the development of automatic evaluation metrics that are reliable in various domains, dimensions, and languages. This track in the 11th Dialogue System Technology Challenge (DSTC11) is part of the ongoing effort to promote robust and multilingual automatic evaluation metrics. This article describes the datasets and baselines provided to participants and discusses the submission and result details of the two proposed subtasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rodriguez-cantelar-etal-2023-overview">
<titleInfo>
<title>Overview of Robust and Multilingual Automatic Evaluation Metricsfor Open-Domain Dialogue Systems at DSTC 11 Track 4</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Rodríguez-Cantelar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengguang</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarik</namePart>
<namePart type="family">Ghazarian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Fernando D’Haro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Rudnicky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Eleventh Dialog System Technology Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Crook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Galley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarik</namePart>
<namePart type="family">Ghazarian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulaka</namePart>
<namePart type="family">Gunasekara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghav</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behnam</namePart>
<namePart type="family">Hedayatnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satwik</namePart>
<namePart type="family">Kottur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungwhan</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</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">Prague, Czech Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The advent and fast development of neural networks have revolutionized the research on dialogue systems and subsequently have triggered various challenges regarding their automatic evaluation. Automatic evaluation of open-domain dialogue systems as an open challenge has been the center of the attention of many researchers. Despite the consistent efforts to improve automatic metrics’ correlations with human evaluation, there have been very few attempts to assess their robustness over multiple domains and dimensions. Also, their focus is mainly on the English language. All of these challenges prompt the development of automatic evaluation metrics that are reliable in various domains, dimensions, and languages. This track in the 11th Dialogue System Technology Challenge (DSTC11) is part of the ongoing effort to promote robust and multilingual automatic evaluation metrics. This article describes the datasets and baselines provided to participants and discusses the submission and result details of the two proposed subtasks.</abstract>
<identifier type="citekey">rodriguez-cantelar-etal-2023-overview</identifier>
<location>
<url>https://aclanthology.org/2023.dstc-1.28</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>260</start>
<end>273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overview of Robust and Multilingual Automatic Evaluation Metricsfor Open-Domain Dialogue Systems at DSTC 11 Track 4
%A Rodríguez-Cantelar, Mario
%A Zhang, Chen
%A Tang, Chengguang
%A Shi, Ke
%A Ghazarian, Sarik
%A Sedoc, João
%A Fernando D’Haro, Luis
%A Rudnicky, Alexander I.
%Y Chen, Yun-Nung
%Y Crook, Paul
%Y Galley, Michel
%Y Ghazarian, Sarik
%Y Gunasekara, Chulaka
%Y Gupta, Raghav
%Y Hedayatnia, Behnam
%Y Kottur, Satwik
%Y Moon, Seungwhan
%Y Zhang, Chen
%S Proceedings of The Eleventh Dialog System Technology Challenge
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czech Republic
%F rodriguez-cantelar-etal-2023-overview
%X The advent and fast development of neural networks have revolutionized the research on dialogue systems and subsequently have triggered various challenges regarding their automatic evaluation. Automatic evaluation of open-domain dialogue systems as an open challenge has been the center of the attention of many researchers. Despite the consistent efforts to improve automatic metrics’ correlations with human evaluation, there have been very few attempts to assess their robustness over multiple domains and dimensions. Also, their focus is mainly on the English language. All of these challenges prompt the development of automatic evaluation metrics that are reliable in various domains, dimensions, and languages. This track in the 11th Dialogue System Technology Challenge (DSTC11) is part of the ongoing effort to promote robust and multilingual automatic evaluation metrics. This article describes the datasets and baselines provided to participants and discusses the submission and result details of the two proposed subtasks.
%U https://aclanthology.org/2023.dstc-1.28
%P 260-273
Markdown (Informal)
[Overview of Robust and Multilingual Automatic Evaluation Metricsfor Open-Domain Dialogue Systems at DSTC 11 Track 4](https://aclanthology.org/2023.dstc-1.28) (Rodríguez-Cantelar et al., DSTC-WS 2023)
ACL
- Mario Rodríguez-Cantelar, Chen Zhang, Chengguang Tang, Ke Shi, Sarik Ghazarian, João Sedoc, Luis Fernando D’Haro, and Alexander I. Rudnicky. 2023. Overview of Robust and Multilingual Automatic Evaluation Metricsfor Open-Domain Dialogue Systems at DSTC 11 Track 4. In Proceedings of The Eleventh Dialog System Technology Challenge, pages 260–273, Prague, Czech Republic. Association for Computational Linguistics.