@inproceedings{c-r-etal-2024-legen,
title = "{L}e{G}en: Complex Information Extraction from Legal sentences using Generative Models",
author = "C R, Chaitra and
Kulkarni, Sankalp and
Sagi, Sai Rama Akash Varma and
Pandey, Shashank and
Yalavarthy, Rohit and
Chakraborty, Dipanjan and
Upadhyay, Prajna Devi",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goan{\textcommabelow{t}}{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preo{\textcommabelow{t}}iuc-Pietro, Daniel and
Spanakis, Gerasimos",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2024",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nllp-1.1",
pages = "1--17",
abstract = "Constructing legal knowledge graphs from unstructured legal texts is a complex challenge due to the intricate nature of legal language. While open information extraction (OIE) techniques can convert text into triples of the form subject, relation, object, they often fall short of capturing the nuanced relationships within lengthy legal sentences, necessitating more sophisticated approaches known as complex information extraction. This paper proposes $LeGen$ {--} an end-to-end approach leveraging pre-trained large language models (GPT-4o, T5, BART) to perform complex information extraction from legal sentences. $LeGen$ learns and represents the discourse structure of legal sentences, capturing both their complexity and semantics. It minimizes error propagation typical in multi-step pipelines and achieves up to a 32.2{\%} gain on the Indian Legal benchmark. Additionally, it demonstrates competitive performance on open information extraction benchmarks. A promising application of the resulting legal knowledge graphs is in developing question-answering systems for government schemes, tailored to the Next Billion Users who struggle with the complexity of legal language. Our code and data are available at https://github.com/prajnaupadhyay/LegalIE",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="c-r-etal-2024-legen">
<titleInfo>
<title>LeGen: Complex Information Extraction from Legal sentences using Generative Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaitra</namePart>
<namePart type="family">C R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sankalp</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Rama</namePart>
<namePart type="given">Akash</namePart>
<namePart type="given">Varma</namePart>
<namePart type="family">Sagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashank</namePart>
<namePart type="family">Pandey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Yalavarthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipanjan</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prajna</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Upadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2024</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">Ilias</namePart>
<namePart type="family">Chalkidis</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">Cătălina</namePart>
<namePart type="family">Goan\textcommabelowtă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preo\textcommabelowtiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Constructing legal knowledge graphs from unstructured legal texts is a complex challenge due to the intricate nature of legal language. While open information extraction (OIE) techniques can convert text into triples of the form subject, relation, object, they often fall short of capturing the nuanced relationships within lengthy legal sentences, necessitating more sophisticated approaches known as complex information extraction. This paper proposes LeGen – an end-to-end approach leveraging pre-trained large language models (GPT-4o, T5, BART) to perform complex information extraction from legal sentences. LeGen learns and represents the discourse structure of legal sentences, capturing both their complexity and semantics. It minimizes error propagation typical in multi-step pipelines and achieves up to a 32.2% gain on the Indian Legal benchmark. Additionally, it demonstrates competitive performance on open information extraction benchmarks. A promising application of the resulting legal knowledge graphs is in developing question-answering systems for government schemes, tailored to the Next Billion Users who struggle with the complexity of legal language. Our code and data are available at https://github.com/prajnaupadhyay/LegalIE</abstract>
<identifier type="citekey">c-r-etal-2024-legen</identifier>
<location>
<url>https://aclanthology.org/2024.nllp-1.1</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LeGen: Complex Information Extraction from Legal sentences using Generative Models
%A C R, Chaitra
%A Kulkarni, Sankalp
%A Sagi, Sai Rama Akash Varma
%A Pandey, Shashank
%A Yalavarthy, Rohit
%A Chakraborty, Dipanjan
%A Upadhyay, Prajna Devi
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goan\textcommabelowtă, Cătălina
%Y Preo\textcommabelowtiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%S Proceedings of the Natural Legal Language Processing Workshop 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F c-r-etal-2024-legen
%X Constructing legal knowledge graphs from unstructured legal texts is a complex challenge due to the intricate nature of legal language. While open information extraction (OIE) techniques can convert text into triples of the form subject, relation, object, they often fall short of capturing the nuanced relationships within lengthy legal sentences, necessitating more sophisticated approaches known as complex information extraction. This paper proposes LeGen – an end-to-end approach leveraging pre-trained large language models (GPT-4o, T5, BART) to perform complex information extraction from legal sentences. LeGen learns and represents the discourse structure of legal sentences, capturing both their complexity and semantics. It minimizes error propagation typical in multi-step pipelines and achieves up to a 32.2% gain on the Indian Legal benchmark. Additionally, it demonstrates competitive performance on open information extraction benchmarks. A promising application of the resulting legal knowledge graphs is in developing question-answering systems for government schemes, tailored to the Next Billion Users who struggle with the complexity of legal language. Our code and data are available at https://github.com/prajnaupadhyay/LegalIE
%U https://aclanthology.org/2024.nllp-1.1
%P 1-17
Markdown (Informal)
[LeGen: Complex Information Extraction from Legal sentences using Generative Models](https://aclanthology.org/2024.nllp-1.1) (C R et al., NLLP 2024)
ACL
- Chaitra C R, Sankalp Kulkarni, Sai Rama Akash Varma Sagi, Shashank Pandey, Rohit Yalavarthy, Dipanjan Chakraborty, and Prajna Devi Upadhyay. 2024. LeGen: Complex Information Extraction from Legal sentences using Generative Models. In Proceedings of the Natural Legal Language Processing Workshop 2024, pages 1–17, Miami, FL, USA. Association for Computational Linguistics.