@inproceedings{salaun-etal-2024-europa,
title = "{EUROPA}: A Legal Multilingual Keyphrase Generation Dataset",
author = {Sala{\"u}n, Olivier and
Piedboeuf, Fr{\'e}d{\'e}ric and
Le Berre, Guillaume and
Alfonso-Hermelo, David and
Langlais, Philippe},
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-long.687/",
doi = "10.18653/v1/2024.acl-long.687",
pages = "12718--12736",
abstract = "Keyphrase generation has primarily been explored within the context of academic research articles, with a particular focus on scientific domains and the English language. In this work, we present EUROPA, a novel dataset for multilingual keyphrase generation in the legal domain. It is derived from legal judgments from the Court of Justice of the European Union (EU), and contains instances in all 24 EU official languages. We run multilingual models on our corpus and analyze the results, showing room for improvement on a domain-specific multilingual corpus such as the one we present."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salaun-etal-2024-europa">
<titleInfo>
<title>EUROPA: A Legal Multilingual Keyphrase Generation Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Salaün</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Piedboeuf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Le Berre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Alfonso-Hermelo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Langlais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Keyphrase generation has primarily been explored within the context of academic research articles, with a particular focus on scientific domains and the English language. In this work, we present EUROPA, a novel dataset for multilingual keyphrase generation in the legal domain. It is derived from legal judgments from the Court of Justice of the European Union (EU), and contains instances in all 24 EU official languages. We run multilingual models on our corpus and analyze the results, showing room for improvement on a domain-specific multilingual corpus such as the one we present.</abstract>
<identifier type="citekey">salaun-etal-2024-europa</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.687</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.687/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12718</start>
<end>12736</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EUROPA: A Legal Multilingual Keyphrase Generation Dataset
%A Salaün, Olivier
%A Piedboeuf, Frédéric
%A Le Berre, Guillaume
%A Alfonso-Hermelo, David
%A Langlais, Philippe
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F salaun-etal-2024-europa
%X Keyphrase generation has primarily been explored within the context of academic research articles, with a particular focus on scientific domains and the English language. In this work, we present EUROPA, a novel dataset for multilingual keyphrase generation in the legal domain. It is derived from legal judgments from the Court of Justice of the European Union (EU), and contains instances in all 24 EU official languages. We run multilingual models on our corpus and analyze the results, showing room for improvement on a domain-specific multilingual corpus such as the one we present.
%R 10.18653/v1/2024.acl-long.687
%U https://aclanthology.org/2024.luhme-long.687/
%U https://doi.org/10.18653/v1/2024.acl-long.687
%P 12718-12736
Markdown (Informal)
[EUROPA: A Legal Multilingual Keyphrase Generation Dataset](https://aclanthology.org/2024.luhme-long.687/) (Salaün et al., ACL 2024)
ACL
- Olivier Salaün, Frédéric Piedboeuf, Guillaume Le Berre, David Alfonso-Hermelo, and Philippe Langlais. 2024. EUROPA: A Legal Multilingual Keyphrase Generation Dataset. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12718–12736, Bangkok, Thailand. Association for Computational Linguistics.