@inproceedings{chen-etal-2021-factuality-checkers,
title = "Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization",
author = "Chen, Yiran and
Liu, Pengfei and
Qiu, Xipeng",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.179",
doi = "10.18653/v1/2021.findings-emnlp.179",
pages = "2082--2095",
abstract = "With the continuous upgrading of the summarization systems driven by deep neural networks, researchers have higher requirements on the quality of the generated summaries, which should be not only fluent and informative but also factually correct. As a result, the field of factual evaluation has developed rapidly recently. Despite its initial progress in evaluating generated summaries, the meta-evaluation methodologies of factuality metrics are limited in their opacity, leading to the insufficient understanding of factuality metrics{'} relative advantages and their applicability. In this paper, we present an adversarial meta-evaluation methodology that allows us to (i) diagnose the fine-grained strengths and weaknesses of 6 existing top-performing metrics over 24 diagnostic test datasets, (ii) search for directions for further improvement by data augmentation. Our observations from this work motivate us to propose several calls for future research. We make all codes, diagnostic test datasets, trained factuality models available: \url{https://github.com/zide05/AdvFact}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2021-factuality-checkers">
<titleInfo>
<title>Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiran</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the continuous upgrading of the summarization systems driven by deep neural networks, researchers have higher requirements on the quality of the generated summaries, which should be not only fluent and informative but also factually correct. As a result, the field of factual evaluation has developed rapidly recently. Despite its initial progress in evaluating generated summaries, the meta-evaluation methodologies of factuality metrics are limited in their opacity, leading to the insufficient understanding of factuality metrics’ relative advantages and their applicability. In this paper, we present an adversarial meta-evaluation methodology that allows us to (i) diagnose the fine-grained strengths and weaknesses of 6 existing top-performing metrics over 24 diagnostic test datasets, (ii) search for directions for further improvement by data augmentation. Our observations from this work motivate us to propose several calls for future research. We make all codes, diagnostic test datasets, trained factuality models available: https://github.com/zide05/AdvFact.</abstract>
<identifier type="citekey">chen-etal-2021-factuality-checkers</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.179</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.179</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2082</start>
<end>2095</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization
%A Chen, Yiran
%A Liu, Pengfei
%A Qiu, Xipeng
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F chen-etal-2021-factuality-checkers
%X With the continuous upgrading of the summarization systems driven by deep neural networks, researchers have higher requirements on the quality of the generated summaries, which should be not only fluent and informative but also factually correct. As a result, the field of factual evaluation has developed rapidly recently. Despite its initial progress in evaluating generated summaries, the meta-evaluation methodologies of factuality metrics are limited in their opacity, leading to the insufficient understanding of factuality metrics’ relative advantages and their applicability. In this paper, we present an adversarial meta-evaluation methodology that allows us to (i) diagnose the fine-grained strengths and weaknesses of 6 existing top-performing metrics over 24 diagnostic test datasets, (ii) search for directions for further improvement by data augmentation. Our observations from this work motivate us to propose several calls for future research. We make all codes, diagnostic test datasets, trained factuality models available: https://github.com/zide05/AdvFact.
%R 10.18653/v1/2021.findings-emnlp.179
%U https://aclanthology.org/2021.findings-emnlp.179
%U https://doi.org/10.18653/v1/2021.findings-emnlp.179
%P 2082-2095
Markdown (Informal)
[Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization](https://aclanthology.org/2021.findings-emnlp.179) (Chen et al., Findings 2021)
ACL