@inproceedings{mohankumar-khapra-2022-active,
title = "Active Evaluation: Efficient {NLG} Evaluation with Few Pairwise Comparisons",
author = "Mohankumar, Akash Kumar and
Khapra, Mitesh",
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.600",
doi = "10.18653/v1/2022.acl-long.600",
pages = "8761--8781",
abstract = "Recent studies have shown the advantages of evaluating NLG systems using pairwise comparisons as opposed to direct assessment. Given $k$ systems, a naive approach for identifying the top-ranked system would be to uniformly obtain pairwise comparisons from all ${k \choose 2}$ pairs of systems. However, this can be very expensive as the number of human annotations required would grow quadratically with $k$. In this work, we introduce Active Evaluation, a framework to efficiently identify the top-ranked system by actively choosing system pairs for comparison using dueling bandit algorithms. We perform extensive experiments with 13 dueling bandits algorithms on 13 NLG evaluation datasets spanning 5 tasks and show that the number of human annotations can be reduced by 80{\%}. To further reduce the number of human annotations, we propose model-based dueling bandit algorithms which combine automatic evaluation metrics with human evaluations. Specifically, we eliminate sub-optimal systems even before the human annotation process and perform human evaluations only on test examples where the automatic metric is highly uncertain. This reduces the number of human annotations required further by 89{\%}. In effect, we show that identifying the top-ranked system requires only a few hundred human annotations, which grow linearly with $k$. Lastly, we provide practical recommendations and best practices to identify the top-ranked system efficiently. Our code has been made publicly available at \url{https://github.com/akashkm99/duelnlg}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohankumar-khapra-2022-active">
<titleInfo>
<title>Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akash</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Mohankumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mitesh</namePart>
<namePart type="family">Khapra</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>Recent studies have shown the advantages of evaluating NLG systems using pairwise comparisons as opposed to direct assessment. Given k systems, a naive approach for identifying the top-ranked system would be to uniformly obtain pairwise comparisons from all k \choose 2 pairs of systems. However, this can be very expensive as the number of human annotations required would grow quadratically with k. In this work, we introduce Active Evaluation, a framework to efficiently identify the top-ranked system by actively choosing system pairs for comparison using dueling bandit algorithms. We perform extensive experiments with 13 dueling bandits algorithms on 13 NLG evaluation datasets spanning 5 tasks and show that the number of human annotations can be reduced by 80%. To further reduce the number of human annotations, we propose model-based dueling bandit algorithms which combine automatic evaluation metrics with human evaluations. Specifically, we eliminate sub-optimal systems even before the human annotation process and perform human evaluations only on test examples where the automatic metric is highly uncertain. This reduces the number of human annotations required further by 89%. In effect, we show that identifying the top-ranked system requires only a few hundred human annotations, which grow linearly with k. Lastly, we provide practical recommendations and best practices to identify the top-ranked system efficiently. Our code has been made publicly available at https://github.com/akashkm99/duelnlg</abstract>
<identifier type="citekey">mohankumar-khapra-2022-active</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.600</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.600</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>8761</start>
<end>8781</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons
%A Mohankumar, Akash Kumar
%A Khapra, Mitesh
%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 mohankumar-khapra-2022-active
%X Recent studies have shown the advantages of evaluating NLG systems using pairwise comparisons as opposed to direct assessment. Given k systems, a naive approach for identifying the top-ranked system would be to uniformly obtain pairwise comparisons from all k \choose 2 pairs of systems. However, this can be very expensive as the number of human annotations required would grow quadratically with k. In this work, we introduce Active Evaluation, a framework to efficiently identify the top-ranked system by actively choosing system pairs for comparison using dueling bandit algorithms. We perform extensive experiments with 13 dueling bandits algorithms on 13 NLG evaluation datasets spanning 5 tasks and show that the number of human annotations can be reduced by 80%. To further reduce the number of human annotations, we propose model-based dueling bandit algorithms which combine automatic evaluation metrics with human evaluations. Specifically, we eliminate sub-optimal systems even before the human annotation process and perform human evaluations only on test examples where the automatic metric is highly uncertain. This reduces the number of human annotations required further by 89%. In effect, we show that identifying the top-ranked system requires only a few hundred human annotations, which grow linearly with k. Lastly, we provide practical recommendations and best practices to identify the top-ranked system efficiently. Our code has been made publicly available at https://github.com/akashkm99/duelnlg
%R 10.18653/v1/2022.acl-long.600
%U https://aclanthology.org/2022.acl-long.600
%U https://doi.org/10.18653/v1/2022.acl-long.600
%P 8761-8781
Markdown (Informal)
[Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons](https://aclanthology.org/2022.acl-long.600) (Mohankumar & Khapra, ACL 2022)
ACL