@inproceedings{simonson-etal-2019-extent,
title = "The Extent of Repetition in Contract Language",
author = "Simonson, Dan and
Broderick, Daniel and
Herr, Jonathan",
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/W19-2203",
doi = "10.18653/v1/W19-2203",
pages = "21--30",
abstract = "Contract language is repetitive (Anderson and Manns, 2017), but so is all language (Zipf, 1949). In this paper, we measure the extent to which contract language in English is repetitive compared with the language of other English language corpora. Contracts have much smaller vocabulary sizes compared with similarly sized non-contract corpora across multiple contract types, contain 1/5th as many hapax legomena, pattern differently on a log-log plot, use fewer pronouns, and contain sentences that are about 20{\%} more similar to one another than in other corpora. These suggest that the study of contracts in natural language processing controls for some linguistic phenomena and allows for more in depth study of others.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simonson-etal-2019-extent">
<titleInfo>
<title>The Extent of Repetition in Contract Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Simonson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Broderick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Herr</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>Contract language is repetitive (Anderson and Manns, 2017), but so is all language (Zipf, 1949). In this paper, we measure the extent to which contract language in English is repetitive compared with the language of other English language corpora. Contracts have much smaller vocabulary sizes compared with similarly sized non-contract corpora across multiple contract types, contain 1/5th as many hapax legomena, pattern differently on a log-log plot, use fewer pronouns, and contain sentences that are about 20% more similar to one another than in other corpora. These suggest that the study of contracts in natural language processing controls for some linguistic phenomena and allows for more in depth study of others.</abstract>
<identifier type="citekey">simonson-etal-2019-extent</identifier>
<identifier type="doi">10.18653/v1/W19-2203</identifier>
<location>
<url>https://aclanthology.org/W19-2203</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>21</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Extent of Repetition in Contract Language
%A Simonson, Dan
%A Broderick, Daniel
%A Herr, Jonathan
%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 simonson-etal-2019-extent
%X Contract language is repetitive (Anderson and Manns, 2017), but so is all language (Zipf, 1949). In this paper, we measure the extent to which contract language in English is repetitive compared with the language of other English language corpora. Contracts have much smaller vocabulary sizes compared with similarly sized non-contract corpora across multiple contract types, contain 1/5th as many hapax legomena, pattern differently on a log-log plot, use fewer pronouns, and contain sentences that are about 20% more similar to one another than in other corpora. These suggest that the study of contracts in natural language processing controls for some linguistic phenomena and allows for more in depth study of others.
%R 10.18653/v1/W19-2203
%U https://aclanthology.org/W19-2203
%U https://doi.org/10.18653/v1/W19-2203
%P 21-30
Markdown (Informal)
[The Extent of Repetition in Contract Language](https://aclanthology.org/W19-2203) (Simonson et al., NAACL 2019)
ACL
- Dan Simonson, Daniel Broderick, and Jonathan Herr. 2019. The Extent of Repetition in Contract Language. In Proceedings of the Natural Legal Language Processing Workshop 2019, pages 21–30, Minneapolis, Minnesota. Association for Computational Linguistics.