@inproceedings{spangher-etal-2024-legaldiscourse,
title = "{L}egal{D}iscourse: Interpreting When Laws Apply and To Whom",
author = "Spangher, Alexander and
Xue, Zihan and
Wu, Te-Lin and
Hansen, Mark and
May, Jonathan",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.472",
pages = "8528--8551",
abstract = "While legal AI has made strides in recent years, it still struggles with basic legal concepts: {\_}when{\_} does a law apply? {\_}Who{\_} does it applies to? {\_}What{\_} does it do? We take a {\_}discourse{\_} approach to addressing these problems and introduce a novel taxonomy for span-and-relation parsing of legal texts. We create a dataset, {\_}LegalDiscourse{\_} of 602 state-level law paragraphs consisting of 3,715 discourse spans and 1,671 relations. Our trained annotators have an agreement-rate $\kappa>.8$, yet few-shot GPT3.5 performs poorly at span identification and relation classification. Although fine-tuning improves performance, GPT3.5 still lags far below human level. We demonstrate the usefulness of our schema by creating a web application with journalists. We collect over 100,000 laws for 52 U.S. states and territories using 20 scrapers we built, and apply our trained models to 6,000 laws using U.S. Census population numbers. We describe two journalistic outputs stemming from this application: (1) an investigation into the increase in liquor licenses following population growth and (2) a decrease in applicable laws under different under-count projections.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spangher-etal-2024-legaldiscourse">
<titleInfo>
<title>LegalDiscourse: Interpreting When Laws Apply and To Whom</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Spangher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Te-Lin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Hansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While legal AI has made strides in recent years, it still struggles with basic legal concepts: _when_ does a law apply? _Who_ does it applies to? _What_ does it do? We take a _discourse_ approach to addressing these problems and introduce a novel taxonomy for span-and-relation parsing of legal texts. We create a dataset, _LegalDiscourse_ of 602 state-level law paragraphs consisting of 3,715 discourse spans and 1,671 relations. Our trained annotators have an agreement-rate Ä…ppa>.8, yet few-shot GPT3.5 performs poorly at span identification and relation classification. Although fine-tuning improves performance, GPT3.5 still lags far below human level. We demonstrate the usefulness of our schema by creating a web application with journalists. We collect over 100,000 laws for 52 U.S. states and territories using 20 scrapers we built, and apply our trained models to 6,000 laws using U.S. Census population numbers. We describe two journalistic outputs stemming from this application: (1) an investigation into the increase in liquor licenses following population growth and (2) a decrease in applicable laws under different under-count projections.</abstract>
<identifier type="citekey">spangher-etal-2024-legaldiscourse</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.472</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>8528</start>
<end>8551</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LegalDiscourse: Interpreting When Laws Apply and To Whom
%A Spangher, Alexander
%A Xue, Zihan
%A Wu, Te-Lin
%A Hansen, Mark
%A May, Jonathan
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F spangher-etal-2024-legaldiscourse
%X While legal AI has made strides in recent years, it still struggles with basic legal concepts: _when_ does a law apply? _Who_ does it applies to? _What_ does it do? We take a _discourse_ approach to addressing these problems and introduce a novel taxonomy for span-and-relation parsing of legal texts. We create a dataset, _LegalDiscourse_ of 602 state-level law paragraphs consisting of 3,715 discourse spans and 1,671 relations. Our trained annotators have an agreement-rate Ä…ppa>.8, yet few-shot GPT3.5 performs poorly at span identification and relation classification. Although fine-tuning improves performance, GPT3.5 still lags far below human level. We demonstrate the usefulness of our schema by creating a web application with journalists. We collect over 100,000 laws for 52 U.S. states and territories using 20 scrapers we built, and apply our trained models to 6,000 laws using U.S. Census population numbers. We describe two journalistic outputs stemming from this application: (1) an investigation into the increase in liquor licenses following population growth and (2) a decrease in applicable laws under different under-count projections.
%U https://aclanthology.org/2024.naacl-long.472
%P 8528-8551
Markdown (Informal)
[LegalDiscourse: Interpreting When Laws Apply and To Whom](https://aclanthology.org/2024.naacl-long.472) (Spangher et al., NAACL 2024)
ACL
- Alexander Spangher, Zihan Xue, Te-Lin Wu, Mark Hansen, and Jonathan May. 2024. LegalDiscourse: Interpreting When Laws Apply and To Whom. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 8528–8551, Mexico City, Mexico. Association for Computational Linguistics.