@inproceedings{tuggener-etal-2020-ledgar,
title = "{LEDGAR}: A Large-Scale Multi-label Corpus for Text Classification of Legal Provisions in Contracts",
author = {Tuggener, Don and
von D{\"a}niken, Pius and
Peetz, Thomas and
Cieliebak, Mark},
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-1.155",
pages = "1235--1241",
abstract = "We present LEDGAR, a multilabel corpus of legal provisions in contracts. The corpus was crawled and scraped from the public domain (SEC filings) and is, to the best of our knowledge, the first freely available corpus of its kind. Since the corpus was constructed semi-automatically, we apply and discuss various approaches to noise removal. Due to the rather large labelset of over 12{'}000 labels annotated in almost 100{'}000 provisions in over 60{'}000 contracts, we believe the corpus to be of interest for research in the field of Legal NLP, (large-scale or extreme) text classification, as well as for legal studies. We discuss several methods to sample subcopora from the corpus and implement and evaluate different automatic classification approaches. Finally, we perform transfer experiments to evaluate how well the classifiers perform on contracts stemming from outside the corpus.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tuggener-etal-2020-ledgar">
<titleInfo>
<title>LEDGAR: A Large-Scale Multi-label Corpus for Text Classification of Legal Provisions in Contracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Don</namePart>
<namePart type="family">Tuggener</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pius</namePart>
<namePart type="family">von Däniken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Peetz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Cieliebak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<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>We present LEDGAR, a multilabel corpus of legal provisions in contracts. The corpus was crawled and scraped from the public domain (SEC filings) and is, to the best of our knowledge, the first freely available corpus of its kind. Since the corpus was constructed semi-automatically, we apply and discuss various approaches to noise removal. Due to the rather large labelset of over 12’000 labels annotated in almost 100’000 provisions in over 60’000 contracts, we believe the corpus to be of interest for research in the field of Legal NLP, (large-scale or extreme) text classification, as well as for legal studies. We discuss several methods to sample subcopora from the corpus and implement and evaluate different automatic classification approaches. Finally, we perform transfer experiments to evaluate how well the classifiers perform on contracts stemming from outside the corpus.</abstract>
<identifier type="citekey">tuggener-etal-2020-ledgar</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.155</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1235</start>
<end>1241</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LEDGAR: A Large-Scale Multi-label Corpus for Text Classification of Legal Provisions in Contracts
%A Tuggener, Don
%A von Däniken, Pius
%A Peetz, Thomas
%A Cieliebak, Mark
%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 English
%F tuggener-etal-2020-ledgar
%X We present LEDGAR, a multilabel corpus of legal provisions in contracts. The corpus was crawled and scraped from the public domain (SEC filings) and is, to the best of our knowledge, the first freely available corpus of its kind. Since the corpus was constructed semi-automatically, we apply and discuss various approaches to noise removal. Due to the rather large labelset of over 12’000 labels annotated in almost 100’000 provisions in over 60’000 contracts, we believe the corpus to be of interest for research in the field of Legal NLP, (large-scale or extreme) text classification, as well as for legal studies. We discuss several methods to sample subcopora from the corpus and implement and evaluate different automatic classification approaches. Finally, we perform transfer experiments to evaluate how well the classifiers perform on contracts stemming from outside the corpus.
%U https://aclanthology.org/2020.lrec-1.155
%P 1235-1241
Markdown (Informal)
[LEDGAR: A Large-Scale Multi-label Corpus for Text Classification of Legal Provisions in Contracts](https://aclanthology.org/2020.lrec-1.155) (Tuggener et al., LREC 2020)
ACL