@inproceedings{elaraby-etal-2024-adding,
title = "Adding Argumentation into Human Evaluation of Long Document Abstractive Summarization: A Case Study on Legal Opinions",
author = "Elaraby, Mohamed and
Xu, Huihui and
Gray, Morgan and
Ashley, Kevin and
Litman, Diane",
editor = "Balloccu, Simone and
Belz, Anya and
Huidrom, Rudali and
Reiter, Ehud and
Sedoc, Joao and
Thomson, Craig",
booktitle = "Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.humeval-1.3",
pages = "28--35",
abstract = "Human evaluation remains the gold standard for assessing abstractive summarization. However, current practices often prioritize constructing evaluation guidelines for fluency, coherence, and factual accuracy, overlooking other critical dimensions. In this paper, we investigate argument coverage in abstractive summarization by focusing on long legal opinions, where summaries must effectively encapsulate the document{'}s argumentative nature. We introduce a set of human-evaluation guidelines to evaluate generated summaries based on argumentative coverage. These guidelines enable us to assess three distinct summarization models, studying the influence of including argument roles in summarization. Furthermore, we utilize these evaluation scores to benchmark automatic summarization metrics against argument coverage, providing insights into the effectiveness of automated evaluation methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elaraby-etal-2024-adding">
<titleInfo>
<title>Adding Argumentation into Human Evaluation of Long Document Abstractive Summarization: A Case Study on Legal Opinions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Elaraby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huihui</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morgan</namePart>
<namePart type="family">Gray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Ashley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Litman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Balloccu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudali</namePart>
<namePart type="family">Huidrom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joao</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Thomson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Human evaluation remains the gold standard for assessing abstractive summarization. However, current practices often prioritize constructing evaluation guidelines for fluency, coherence, and factual accuracy, overlooking other critical dimensions. In this paper, we investigate argument coverage in abstractive summarization by focusing on long legal opinions, where summaries must effectively encapsulate the document’s argumentative nature. We introduce a set of human-evaluation guidelines to evaluate generated summaries based on argumentative coverage. These guidelines enable us to assess three distinct summarization models, studying the influence of including argument roles in summarization. Furthermore, we utilize these evaluation scores to benchmark automatic summarization metrics against argument coverage, providing insights into the effectiveness of automated evaluation methods.</abstract>
<identifier type="citekey">elaraby-etal-2024-adding</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.3</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>28</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adding Argumentation into Human Evaluation of Long Document Abstractive Summarization: A Case Study on Legal Opinions
%A Elaraby, Mohamed
%A Xu, Huihui
%A Gray, Morgan
%A Ashley, Kevin
%A Litman, Diane
%Y Balloccu, Simone
%Y Belz, Anya
%Y Huidrom, Rudali
%Y Reiter, Ehud
%Y Sedoc, Joao
%Y Thomson, Craig
%S Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F elaraby-etal-2024-adding
%X Human evaluation remains the gold standard for assessing abstractive summarization. However, current practices often prioritize constructing evaluation guidelines for fluency, coherence, and factual accuracy, overlooking other critical dimensions. In this paper, we investigate argument coverage in abstractive summarization by focusing on long legal opinions, where summaries must effectively encapsulate the document’s argumentative nature. We introduce a set of human-evaluation guidelines to evaluate generated summaries based on argumentative coverage. These guidelines enable us to assess three distinct summarization models, studying the influence of including argument roles in summarization. Furthermore, we utilize these evaluation scores to benchmark automatic summarization metrics against argument coverage, providing insights into the effectiveness of automated evaluation methods.
%U https://aclanthology.org/2024.humeval-1.3
%P 28-35
Markdown (Informal)
[Adding Argumentation into Human Evaluation of Long Document Abstractive Summarization: A Case Study on Legal Opinions](https://aclanthology.org/2024.humeval-1.3) (Elaraby et al., HumEval-WS 2024)
ACL