@inproceedings{tan-etal-2024-towards-automated,
title = "Towards an Automated Pointwise Evaluation Metric for Generated Long-Form Legal Summaries",
author = "Tan, Shao Min and
Grail, Quentin and
Quartey, Lee",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goan{\textcommabelow{t}}{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preo{\textcommabelow{t}}iuc-Pietro, Daniel and
Spanakis, Gerasimos",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2024",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nllp-1.10",
pages = "129--142",
abstract = "Long-form abstractive summarization is a task that has particular importance in the legal domain. Automated evaluation metrics are important for the development of text generation models, but existing research on the evaluation of generated summaries has focused mainly on short summaries. We introduce an automated evaluation methodology for generated long-form legal summaries, which involves breaking each summary into individual points, comparing the points in a human-written and machine-generated summary, and calculating a recall and precision score for the latter. The method is designed to be particularly suited for the complexities of legal text, and is also fully interpretable. We also create and release a small meta-dataset for the benchmarking of evaluation methods, focusing on long-form legal summarization. Our evaluation metric corresponds better with human evaluation compared to existing metrics which were not developed for legal data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2024-towards-automated">
<titleInfo>
<title>Towards an Automated Pointwise Evaluation Metric for Generated Long-Form Legal Summaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shao</namePart>
<namePart type="given">Min</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quentin</namePart>
<namePart type="family">Grail</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lee</namePart>
<namePart type="family">Quartey</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 Natural Legal Language Processing Workshop 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goan\textcommabelowtă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preo\textcommabelowtiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Long-form abstractive summarization is a task that has particular importance in the legal domain. Automated evaluation metrics are important for the development of text generation models, but existing research on the evaluation of generated summaries has focused mainly on short summaries. We introduce an automated evaluation methodology for generated long-form legal summaries, which involves breaking each summary into individual points, comparing the points in a human-written and machine-generated summary, and calculating a recall and precision score for the latter. The method is designed to be particularly suited for the complexities of legal text, and is also fully interpretable. We also create and release a small meta-dataset for the benchmarking of evaluation methods, focusing on long-form legal summarization. Our evaluation metric corresponds better with human evaluation compared to existing metrics which were not developed for legal data.</abstract>
<identifier type="citekey">tan-etal-2024-towards-automated</identifier>
<location>
<url>https://aclanthology.org/2024.nllp-1.10</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>129</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards an Automated Pointwise Evaluation Metric for Generated Long-Form Legal Summaries
%A Tan, Shao Min
%A Grail, Quentin
%A Quartey, Lee
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goan\textcommabelowtă, Cătălina
%Y Preo\textcommabelowtiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%S Proceedings of the Natural Legal Language Processing Workshop 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F tan-etal-2024-towards-automated
%X Long-form abstractive summarization is a task that has particular importance in the legal domain. Automated evaluation metrics are important for the development of text generation models, but existing research on the evaluation of generated summaries has focused mainly on short summaries. We introduce an automated evaluation methodology for generated long-form legal summaries, which involves breaking each summary into individual points, comparing the points in a human-written and machine-generated summary, and calculating a recall and precision score for the latter. The method is designed to be particularly suited for the complexities of legal text, and is also fully interpretable. We also create and release a small meta-dataset for the benchmarking of evaluation methods, focusing on long-form legal summarization. Our evaluation metric corresponds better with human evaluation compared to existing metrics which were not developed for legal data.
%U https://aclanthology.org/2024.nllp-1.10
%P 129-142
Markdown (Informal)
[Towards an Automated Pointwise Evaluation Metric for Generated Long-Form Legal Summaries](https://aclanthology.org/2024.nllp-1.10) (Tan et al., NLLP 2024)
ACL