@inproceedings{gigant-etal-2024-mitigating,
title = "Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics",
author = "Gigant, Th{\'e}o and
Guinaudeau, Camille and
Decombas, Marc and
Dufaux, Frederic",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1078",
pages = "19355--19368",
abstract = "Automatic metrics are used as proxies to evaluate abstractive summarization systems when human annotations are too expensive. To be useful, these metrics should be fine-grained, show a high correlation with human annotations, and ideally be independant of reference quality; however, most standard evaluation metrics for summarization are reference-based, and existing reference-free metrics correlates poorly with relevance, especially on summaries of longer documents. In this paper, we introduce a reference-free metric that correlates well with human evaluated relevance, while being very cheap to compute. We show that this metric can also be used along reference-based metrics to improve their robustness in low quality reference settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gigant-etal-2024-mitigating">
<titleInfo>
<title>Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Théo</namePart>
<namePart type="family">Gigant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camille</namePart>
<namePart type="family">Guinaudeau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Decombas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Dufaux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic metrics are used as proxies to evaluate abstractive summarization systems when human annotations are too expensive. To be useful, these metrics should be fine-grained, show a high correlation with human annotations, and ideally be independant of reference quality; however, most standard evaluation metrics for summarization are reference-based, and existing reference-free metrics correlates poorly with relevance, especially on summaries of longer documents. In this paper, we introduce a reference-free metric that correlates well with human evaluated relevance, while being very cheap to compute. We show that this metric can also be used along reference-based metrics to improve their robustness in low quality reference settings.</abstract>
<identifier type="citekey">gigant-etal-2024-mitigating</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.1078</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>19355</start>
<end>19368</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics
%A Gigant, Théo
%A Guinaudeau, Camille
%A Decombas, Marc
%A Dufaux, Frederic
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F gigant-etal-2024-mitigating
%X Automatic metrics are used as proxies to evaluate abstractive summarization systems when human annotations are too expensive. To be useful, these metrics should be fine-grained, show a high correlation with human annotations, and ideally be independant of reference quality; however, most standard evaluation metrics for summarization are reference-based, and existing reference-free metrics correlates poorly with relevance, especially on summaries of longer documents. In this paper, we introduce a reference-free metric that correlates well with human evaluated relevance, while being very cheap to compute. We show that this metric can also be used along reference-based metrics to improve their robustness in low quality reference settings.
%U https://aclanthology.org/2024.emnlp-main.1078
%P 19355-19368
Markdown (Informal)
[Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics](https://aclanthology.org/2024.emnlp-main.1078) (Gigant et al., EMNLP 2024)
ACL