@inproceedings{avram-etal-2021-pyeurovoc,
title = "{P}y{E}uro{V}oc: A Tool for Multilingual Legal Document Classification with {E}uro{V}oc Descriptors",
author = "Avram, Andrei-Marius and
Pais, Vasile and
Tufis, Dan Ioan",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.12",
pages = "92--101",
abstract = "EuroVoc is a multilingual thesaurus that was built for organizing the legislative documentary of the European Union institutions. It contains thousands of categories at different levels of specificity and its descriptors are targeted by legal texts in almost thirty languages. In this work we propose a unified framework for EuroVoc classification on 22 languages by fine-tuning modern Transformer-based pretrained language models. We study extensively the performance of our trained models and show that they significantly improve the results obtained by a similar tool - JEX - on the same dataset. The code and the fine-tuned models were open sourced, together with a programmatic interface that eases the process of loading the weights of a trained model and of classifying a new document.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="avram-etal-2021-pyeurovoc">
<titleInfo>
<title>PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrei-Marius</namePart>
<namePart type="family">Avram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasile</namePart>
<namePart type="family">Pais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="given">Ioan</namePart>
<namePart type="family">Tufis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-sep</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>EuroVoc is a multilingual thesaurus that was built for organizing the legislative documentary of the European Union institutions. It contains thousands of categories at different levels of specificity and its descriptors are targeted by legal texts in almost thirty languages. In this work we propose a unified framework for EuroVoc classification on 22 languages by fine-tuning modern Transformer-based pretrained language models. We study extensively the performance of our trained models and show that they significantly improve the results obtained by a similar tool - JEX - on the same dataset. The code and the fine-tuned models were open sourced, together with a programmatic interface that eases the process of loading the weights of a trained model and of classifying a new document.</abstract>
<identifier type="citekey">avram-etal-2021-pyeurovoc</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.12</url>
</location>
<part>
<date>2021-sep</date>
<extent unit="page">
<start>92</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors
%A Avram, Andrei-Marius
%A Pais, Vasile
%A Tufis, Dan Ioan
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 sep
%I INCOMA Ltd.
%C Held Online
%F avram-etal-2021-pyeurovoc
%X EuroVoc is a multilingual thesaurus that was built for organizing the legislative documentary of the European Union institutions. It contains thousands of categories at different levels of specificity and its descriptors are targeted by legal texts in almost thirty languages. In this work we propose a unified framework for EuroVoc classification on 22 languages by fine-tuning modern Transformer-based pretrained language models. We study extensively the performance of our trained models and show that they significantly improve the results obtained by a similar tool - JEX - on the same dataset. The code and the fine-tuned models were open sourced, together with a programmatic interface that eases the process of loading the weights of a trained model and of classifying a new document.
%U https://aclanthology.org/2021.ranlp-1.12
%P 92-101
Markdown (Informal)
[PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors](https://aclanthology.org/2021.ranlp-1.12) (Avram et al., RANLP 2021)
ACL