@inproceedings{chalkidis-etal-2019-extreme,
title = "Extreme Multi-Label Legal Text Classification: A Case Study in {EU} Legislation",
author = "Chalkidis, Ilias and
Fergadiotis, Emmanouil and
Malakasiotis, Prodromos and
Aletras, Nikolaos and
Androutsopoulos, Ion",
editor = "Aletras, Nikolaos and
Ash, Elliott and
Barrett, Leslie and
Chen, Daniel and
Meyers, Adam and
Preotiuc-Pietro, Daniel and
Rosenberg, David and
Stent, Amanda",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2019",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-2209",
doi = "10.18653/v1/W19-2209",
pages = "78--87",
abstract = "We consider the task of Extreme Multi-Label Text Classification (XMTC) in the legal domain. We release a new dataset of 57k legislative documents from EURLEX, the European Union{'}s public document database, annotated with concepts from EUROVOC, a multidisciplinary thesaurus. The dataset is substantially larger than previous EURLEX datasets and suitable for XMTC, few-shot and zero-shot learning. Experimenting with several neural classifiers, we show that BIGRUs with self-attention outperform the current multi-label state-of-the-art methods, which employ label-wise attention. Replacing CNNs with BIGRUs in label-wise attention networks leads to the best overall performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chalkidis-etal-2019-extreme">
<titleInfo>
<title>Extreme Multi-Label Legal Text Classification: A Case Study in EU Legislation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanouil</namePart>
<namePart type="family">Fergadiotis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prodromos</namePart>
<namePart type="family">Malakasiotis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ion</namePart>
<namePart type="family">Androutsopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2019</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">Elliott</namePart>
<namePart type="family">Ash</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">Daniel</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Meyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preotiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Rosenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We consider the task of Extreme Multi-Label Text Classification (XMTC) in the legal domain. We release a new dataset of 57k legislative documents from EURLEX, the European Union’s public document database, annotated with concepts from EUROVOC, a multidisciplinary thesaurus. The dataset is substantially larger than previous EURLEX datasets and suitable for XMTC, few-shot and zero-shot learning. Experimenting with several neural classifiers, we show that BIGRUs with self-attention outperform the current multi-label state-of-the-art methods, which employ label-wise attention. Replacing CNNs with BIGRUs in label-wise attention networks leads to the best overall performance.</abstract>
<identifier type="citekey">chalkidis-etal-2019-extreme</identifier>
<identifier type="doi">10.18653/v1/W19-2209</identifier>
<location>
<url>https://aclanthology.org/W19-2209</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>78</start>
<end>87</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extreme Multi-Label Legal Text Classification: A Case Study in EU Legislation
%A Chalkidis, Ilias
%A Fergadiotis, Emmanouil
%A Malakasiotis, Prodromos
%A Aletras, Nikolaos
%A Androutsopoulos, Ion
%Y Aletras, Nikolaos
%Y Ash, Elliott
%Y Barrett, Leslie
%Y Chen, Daniel
%Y Meyers, Adam
%Y Preotiuc-Pietro, Daniel
%Y Rosenberg, David
%Y Stent, Amanda
%S Proceedings of the Natural Legal Language Processing Workshop 2019
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F chalkidis-etal-2019-extreme
%X We consider the task of Extreme Multi-Label Text Classification (XMTC) in the legal domain. We release a new dataset of 57k legislative documents from EURLEX, the European Union’s public document database, annotated with concepts from EUROVOC, a multidisciplinary thesaurus. The dataset is substantially larger than previous EURLEX datasets and suitable for XMTC, few-shot and zero-shot learning. Experimenting with several neural classifiers, we show that BIGRUs with self-attention outperform the current multi-label state-of-the-art methods, which employ label-wise attention. Replacing CNNs with BIGRUs in label-wise attention networks leads to the best overall performance.
%R 10.18653/v1/W19-2209
%U https://aclanthology.org/W19-2209
%U https://doi.org/10.18653/v1/W19-2209
%P 78-87
Markdown (Informal)
[Extreme Multi-Label Legal Text Classification: A Case Study in EU Legislation](https://aclanthology.org/W19-2209) (Chalkidis et al., NAACL 2019)
ACL