@inproceedings{soh-etal-2019-legal,
title = "Legal Area Classification: A Comparative Study of Text Classifiers on {S}ingapore {S}upreme {C}ourt Judgments",
author = "Soh, Jerrold and
Lim, How Khang and
Chai, Ian Ernst",
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/W19-2208",
doi = "10.18653/v1/W19-2208",
pages = "67--77",
abstract = "This paper conducts a comparative study on the performance of various machine learning approaches for classifying judgments into legal areas. Using a novel dataset of 6,227 Singapore Supreme Court judgments, we investigate how state-of-the-art NLP methods compare against traditional statistical models when applied to a legal corpus that comprised few but lengthy documents. All approaches tested, including topic model, word embedding, and language model-based classifiers, performed well with as little as a few hundred judgments. However, more work needs to be done to optimize state-of-the-art methods for the legal domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="soh-etal-2019-legal">
<titleInfo>
<title>Legal Area Classification: A Comparative Study of Text Classifiers on Singapore Supreme Court Judgments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jerrold</namePart>
<namePart type="family">Soh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">How</namePart>
<namePart type="given">Khang</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="given">Ernst</namePart>
<namePart type="family">Chai</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>This paper conducts a comparative study on the performance of various machine learning approaches for classifying judgments into legal areas. Using a novel dataset of 6,227 Singapore Supreme Court judgments, we investigate how state-of-the-art NLP methods compare against traditional statistical models when applied to a legal corpus that comprised few but lengthy documents. All approaches tested, including topic model, word embedding, and language model-based classifiers, performed well with as little as a few hundred judgments. However, more work needs to be done to optimize state-of-the-art methods for the legal domain.</abstract>
<identifier type="citekey">soh-etal-2019-legal</identifier>
<identifier type="doi">10.18653/v1/W19-2208</identifier>
<location>
<url>https://aclanthology.org/W19-2208</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>67</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Legal Area Classification: A Comparative Study of Text Classifiers on Singapore Supreme Court Judgments
%A Soh, Jerrold
%A Lim, How Khang
%A Chai, Ian Ernst
%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 soh-etal-2019-legal
%X This paper conducts a comparative study on the performance of various machine learning approaches for classifying judgments into legal areas. Using a novel dataset of 6,227 Singapore Supreme Court judgments, we investigate how state-of-the-art NLP methods compare against traditional statistical models when applied to a legal corpus that comprised few but lengthy documents. All approaches tested, including topic model, word embedding, and language model-based classifiers, performed well with as little as a few hundred judgments. However, more work needs to be done to optimize state-of-the-art methods for the legal domain.
%R 10.18653/v1/W19-2208
%U https://aclanthology.org/W19-2208
%U https://doi.org/10.18653/v1/W19-2208
%P 67-77
Markdown (Informal)
[Legal Area Classification: A Comparative Study of Text Classifiers on Singapore Supreme Court Judgments](https://aclanthology.org/W19-2208) (Soh et al., NAACL 2019)
ACL