@inproceedings{ridenour-etal-2022-assessing,
title = "Assessing Inter-metric Correlation for Multi-document Summarization Evaluation",
author = "Ridenour, Michael and
Agrawal, Ameeta and
Olabisi, Olubusayo",
editor = "Bosselut, Antoine and
Chandu, Khyathi and
Dhole, Kaustubh and
Gangal, Varun and
Gehrmann, Sebastian and
Jernite, Yacine and
Novikova, Jekaterina and
Perez-Beltrachini, Laura",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gem-1.40",
doi = "10.18653/v1/2022.gem-1.40",
pages = "428--438",
abstract = "Recent advances in automatic text summarization have contemporaneously been accompanied by a great deal of new metrics of automatic evaluation. This in turn has inspired recent research to re-assess these evaluation metrics to see how well they correlate with each other as well as with human evaluation, mostly focusing on single-document summarization (SDS) tasks. Although many of these metrics are typically also used for evaluating multi-document summarization (MDS) tasks, so far, little attention has been paid to studying them under such a distinct scenario. To address this gap, we present a systematic analysis of the inter-metric correlations for MDS tasks, while comparing and contrasting the results with SDS models. Using datasets from a wide range of domains (news, peer reviews, tweets, dialogues), we thus study a unified set of metrics under both the task setups. Our empirical analysis suggests that while most reference-based metrics show fairly similar trends across both multi- and single-document summarization, there is a notable lack of correlation between reference-free metrics in multi-document summarization tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ridenour-etal-2022-assessing">
<titleInfo>
<title>Assessing Inter-metric Correlation for Multi-document Summarization Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Ridenour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ameeta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olubusayo</namePart>
<namePart type="family">Olabisi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in automatic text summarization have contemporaneously been accompanied by a great deal of new metrics of automatic evaluation. This in turn has inspired recent research to re-assess these evaluation metrics to see how well they correlate with each other as well as with human evaluation, mostly focusing on single-document summarization (SDS) tasks. Although many of these metrics are typically also used for evaluating multi-document summarization (MDS) tasks, so far, little attention has been paid to studying them under such a distinct scenario. To address this gap, we present a systematic analysis of the inter-metric correlations for MDS tasks, while comparing and contrasting the results with SDS models. Using datasets from a wide range of domains (news, peer reviews, tweets, dialogues), we thus study a unified set of metrics under both the task setups. Our empirical analysis suggests that while most reference-based metrics show fairly similar trends across both multi- and single-document summarization, there is a notable lack of correlation between reference-free metrics in multi-document summarization tasks.</abstract>
<identifier type="citekey">ridenour-etal-2022-assessing</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.40</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.40</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>428</start>
<end>438</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing Inter-metric Correlation for Multi-document Summarization Evaluation
%A Ridenour, Michael
%A Agrawal, Ameeta
%A Olabisi, Olubusayo
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F ridenour-etal-2022-assessing
%X Recent advances in automatic text summarization have contemporaneously been accompanied by a great deal of new metrics of automatic evaluation. This in turn has inspired recent research to re-assess these evaluation metrics to see how well they correlate with each other as well as with human evaluation, mostly focusing on single-document summarization (SDS) tasks. Although many of these metrics are typically also used for evaluating multi-document summarization (MDS) tasks, so far, little attention has been paid to studying them under such a distinct scenario. To address this gap, we present a systematic analysis of the inter-metric correlations for MDS tasks, while comparing and contrasting the results with SDS models. Using datasets from a wide range of domains (news, peer reviews, tweets, dialogues), we thus study a unified set of metrics under both the task setups. Our empirical analysis suggests that while most reference-based metrics show fairly similar trends across both multi- and single-document summarization, there is a notable lack of correlation between reference-free metrics in multi-document summarization tasks.
%R 10.18653/v1/2022.gem-1.40
%U https://aclanthology.org/2022.gem-1.40
%U https://doi.org/10.18653/v1/2022.gem-1.40
%P 428-438
Markdown (Informal)
[Assessing Inter-metric Correlation for Multi-document Summarization Evaluation](https://aclanthology.org/2022.gem-1.40) (Ridenour et al., GEM 2022)
ACL