@inproceedings{luz-de-araujo-etal-2020-victor,
title = "{VICTOR}: a Dataset for {B}razilian Legal Documents Classification",
author = "Luz de Araujo, Pedro Henrique and
de Campos, Te{\'o}filo Em{\'i}dio and
Ataides Braz, Fabricio and
Correia da Silva, Nilton",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.181/",
pages = "1449--1458",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "This paper describes VICTOR, a novel dataset built from Brazil`s Supreme Court digitalized legal documents, composed of more than 45 thousand appeals, which includes roughly 692 thousand documents{---}about 4.6 million pages. The dataset contains labeled text data and supports two types of tasks: document type classification; and theme assignment, a multilabel problem. We present baseline results using bag-of-words models, convolutional neural networks, recurrent neural networks and boosting algorithms. We also experiment using linear-chain Conditional Random Fields to leverage the sequential nature of the lawsuits, which we find to lead to improvements on document type classification. Finally we compare a theme classification approach where we use domain knowledge to filter out the less informative document pages to the default one where we use all pages. Contrary to the Court experts' expectations, we find that using all available data is the better method. We make the dataset available in three versions of different sizes and contents to encourage explorations of better models and techniques."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luz-de-araujo-etal-2020-victor">
<titleInfo>
<title>VICTOR: a Dataset for Brazilian Legal Documents Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="family">Luz de Araujo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teófilo</namePart>
<namePart type="given">Emídio</namePart>
<namePart type="family">de Campos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabricio</namePart>
<namePart type="family">Ataides Braz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nilton</namePart>
<namePart type="family">Correia da Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This paper describes VICTOR, a novel dataset built from Brazil‘s Supreme Court digitalized legal documents, composed of more than 45 thousand appeals, which includes roughly 692 thousand documents—about 4.6 million pages. The dataset contains labeled text data and supports two types of tasks: document type classification; and theme assignment, a multilabel problem. We present baseline results using bag-of-words models, convolutional neural networks, recurrent neural networks and boosting algorithms. We also experiment using linear-chain Conditional Random Fields to leverage the sequential nature of the lawsuits, which we find to lead to improvements on document type classification. Finally we compare a theme classification approach where we use domain knowledge to filter out the less informative document pages to the default one where we use all pages. Contrary to the Court experts’ expectations, we find that using all available data is the better method. We make the dataset available in three versions of different sizes and contents to encourage explorations of better models and techniques.</abstract>
<identifier type="citekey">luz-de-araujo-etal-2020-victor</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.181/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1449</start>
<end>1458</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VICTOR: a Dataset for Brazilian Legal Documents Classification
%A Luz de Araujo, Pedro Henrique
%A de Campos, Teófilo Emídio
%A Ataides Braz, Fabricio
%A Correia da Silva, Nilton
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F luz-de-araujo-etal-2020-victor
%X This paper describes VICTOR, a novel dataset built from Brazil‘s Supreme Court digitalized legal documents, composed of more than 45 thousand appeals, which includes roughly 692 thousand documents—about 4.6 million pages. The dataset contains labeled text data and supports two types of tasks: document type classification; and theme assignment, a multilabel problem. We present baseline results using bag-of-words models, convolutional neural networks, recurrent neural networks and boosting algorithms. We also experiment using linear-chain Conditional Random Fields to leverage the sequential nature of the lawsuits, which we find to lead to improvements on document type classification. Finally we compare a theme classification approach where we use domain knowledge to filter out the less informative document pages to the default one where we use all pages. Contrary to the Court experts’ expectations, we find that using all available data is the better method. We make the dataset available in three versions of different sizes and contents to encourage explorations of better models and techniques.
%U https://aclanthology.org/2020.lrec-1.181/
%P 1449-1458
Markdown (Informal)
[VICTOR: a Dataset for Brazilian Legal Documents Classification](https://aclanthology.org/2020.lrec-1.181/) (Luz de Araujo et al., LREC 2020)
ACL
- Pedro Henrique Luz de Araujo, Teófilo Emídio de Campos, Fabricio Ataides Braz, and Nilton Correia da Silva. 2020. VICTOR: a Dataset for Brazilian Legal Documents Classification. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 1449–1458, Marseille, France. European Language Resources Association.