@inproceedings{finch-etal-2024-exploring,
title = "Exploring the Impact of Human Evaluator Group on Chat-Oriented Dialogue Evaluation",
author = "Finch, Sarah E. and
Finch, James D. and
Choi, Jinho D.",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.610/",
pages = "6966--6973",
abstract = "Human evaluation has been widely accepted as the standard for evaluating chat-oriented dialogue systems. However, there is a significant variation in previous work regarding who gets recruited as evaluators. Evaluator groups such as domain experts, university students, and crowdworkers have been used to assess and compare dialogue systems, although it is unclear to what extent the choice of an evaluator group can affect results. This paper analyzes the evaluator group impact on dialogue system evaluation by testing 4 state-of-the-art dialogue systems using 4 distinct evaluator groups. Our analysis reveals a robustness towards evaluator groups for Likert evaluations that is not seen for Pairwise, with only minor differences observed when changing evaluator groups. Furthermore, two notable limitations to this robustness are observed, which reveal discrepancies between evaluators with different levels of chatbot expertise and indicate that evaluator objectivity is beneficial for certain dialogue metrics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="finch-etal-2024-exploring">
<titleInfo>
<title>Exploring the Impact of Human Evaluator Group on Chat-Oriented Dialogue Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Human evaluation has been widely accepted as the standard for evaluating chat-oriented dialogue systems. However, there is a significant variation in previous work regarding who gets recruited as evaluators. Evaluator groups such as domain experts, university students, and crowdworkers have been used to assess and compare dialogue systems, although it is unclear to what extent the choice of an evaluator group can affect results. This paper analyzes the evaluator group impact on dialogue system evaluation by testing 4 state-of-the-art dialogue systems using 4 distinct evaluator groups. Our analysis reveals a robustness towards evaluator groups for Likert evaluations that is not seen for Pairwise, with only minor differences observed when changing evaluator groups. Furthermore, two notable limitations to this robustness are observed, which reveal discrepancies between evaluators with different levels of chatbot expertise and indicate that evaluator objectivity is beneficial for certain dialogue metrics.</abstract>
<identifier type="citekey">finch-etal-2024-exploring</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.610/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6966</start>
<end>6973</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Impact of Human Evaluator Group on Chat-Oriented Dialogue Evaluation
%A Finch, Sarah E.
%A Finch, James D.
%A Choi, Jinho D.
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F finch-etal-2024-exploring
%X Human evaluation has been widely accepted as the standard for evaluating chat-oriented dialogue systems. However, there is a significant variation in previous work regarding who gets recruited as evaluators. Evaluator groups such as domain experts, university students, and crowdworkers have been used to assess and compare dialogue systems, although it is unclear to what extent the choice of an evaluator group can affect results. This paper analyzes the evaluator group impact on dialogue system evaluation by testing 4 state-of-the-art dialogue systems using 4 distinct evaluator groups. Our analysis reveals a robustness towards evaluator groups for Likert evaluations that is not seen for Pairwise, with only minor differences observed when changing evaluator groups. Furthermore, two notable limitations to this robustness are observed, which reveal discrepancies between evaluators with different levels of chatbot expertise and indicate that evaluator objectivity is beneficial for certain dialogue metrics.
%U https://aclanthology.org/2024.lrec-main.610/
%P 6966-6973
Markdown (Informal)
[Exploring the Impact of Human Evaluator Group on Chat-Oriented Dialogue Evaluation](https://aclanthology.org/2024.lrec-main.610/) (Finch et al., LREC-COLING 2024)
ACL