@inproceedings{mukobara-etal-2024-rethinking,
title = "Rethinking Loss Functions for Fact Verification",
author = "Mukobara, Yuta and
Shigeto, Yutaro and
Shimbo, Masashi",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-short.38",
pages = "432--442",
abstract = "We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this paper, we develop two task-specific objectives tailored to FEVER. Experimental results confirm that the proposed objective functions outperform the standard cross-entropy. Performance is further improved when these objectives are combined with simple class weighting, which effectively overcomes the imbalance in the training data. The source code is available (https://github.com/yuta-mukobara/RLF-KGAT).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mukobara-etal-2024-rethinking">
<titleInfo>
<title>Rethinking Loss Functions for Fact Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Mukobara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutaro</namePart>
<namePart type="family">Shigeto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masashi</namePart>
<namePart type="family">Shimbo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this paper, we develop two task-specific objectives tailored to FEVER. Experimental results confirm that the proposed objective functions outperform the standard cross-entropy. Performance is further improved when these objectives are combined with simple class weighting, which effectively overcomes the imbalance in the training data. The source code is available (https://github.com/yuta-mukobara/RLF-KGAT).</abstract>
<identifier type="citekey">mukobara-etal-2024-rethinking</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-short.38</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>432</start>
<end>442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Loss Functions for Fact Verification
%A Mukobara, Yuta
%A Shigeto, Yutaro
%A Shimbo, Masashi
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F mukobara-etal-2024-rethinking
%X We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this paper, we develop two task-specific objectives tailored to FEVER. Experimental results confirm that the proposed objective functions outperform the standard cross-entropy. Performance is further improved when these objectives are combined with simple class weighting, which effectively overcomes the imbalance in the training data. The source code is available (https://github.com/yuta-mukobara/RLF-KGAT).
%U https://aclanthology.org/2024.eacl-short.38
%P 432-442
Markdown (Informal)
[Rethinking Loss Functions for Fact Verification](https://aclanthology.org/2024.eacl-short.38) (Mukobara et al., EACL 2024)
ACL
- Yuta Mukobara, Yutaro Shigeto, and Masashi Shimbo. 2024. Rethinking Loss Functions for Fact Verification. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 432–442, St. Julian’s, Malta. Association for Computational Linguistics.