@inproceedings{barale-etal-2023-automated,
title = "Automated Refugee Case Analysis: An {NLP} Pipeline for Supporting Legal Practitioners",
author = "Barale, Claire and
Rovatsos, Michael and
Bhuta, Nehal",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.187/",
doi = "10.18653/v1/2023.findings-acl.187",
pages = "2992--3005",
abstract = "In this paper, we introduce an end-to-end pipeline for retrieving, processing, and extracting targeted information from legal cases. We investigate an under-studied legal domain with a case study on refugee law Canada. Searching case law for past similar cases is a key part of legal work for both lawyers and judges, the potential end-users of our prototype. While traditional named-entity recognition labels such as dates are meaningful information in law, we propose to extend existing models and retrieve a total of 19 categories of items from refugee cases. After creating a novel data set of cases, we perform information extraction based on state-of-the-art neural named-entity recognition (NER). We test different architectures including two transformer models, using contextual and non-contextual embeddings, and compare general purpose versus domain-specific pre-training. The results demonstrate that models pre-trained on legal data perform best despite their smaller size, suggesting that domain-matching had a larger effect than network architecture. We achieve a F1- score superior to 90{\%} on five of the targeted categories and superior to 80{\%} on an additional 4 categories."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barale-etal-2023-automated">
<titleInfo>
<title>Automated Refugee Case Analysis: An NLP Pipeline for Supporting Legal Practitioners</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Barale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Rovatsos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nehal</namePart>
<namePart type="family">Bhuta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we introduce an end-to-end pipeline for retrieving, processing, and extracting targeted information from legal cases. We investigate an under-studied legal domain with a case study on refugee law Canada. Searching case law for past similar cases is a key part of legal work for both lawyers and judges, the potential end-users of our prototype. While traditional named-entity recognition labels such as dates are meaningful information in law, we propose to extend existing models and retrieve a total of 19 categories of items from refugee cases. After creating a novel data set of cases, we perform information extraction based on state-of-the-art neural named-entity recognition (NER). We test different architectures including two transformer models, using contextual and non-contextual embeddings, and compare general purpose versus domain-specific pre-training. The results demonstrate that models pre-trained on legal data perform best despite their smaller size, suggesting that domain-matching had a larger effect than network architecture. We achieve a F1- score superior to 90% on five of the targeted categories and superior to 80% on an additional 4 categories.</abstract>
<identifier type="citekey">barale-etal-2023-automated</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.187</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.187/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>2992</start>
<end>3005</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Refugee Case Analysis: An NLP Pipeline for Supporting Legal Practitioners
%A Barale, Claire
%A Rovatsos, Michael
%A Bhuta, Nehal
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F barale-etal-2023-automated
%X In this paper, we introduce an end-to-end pipeline for retrieving, processing, and extracting targeted information from legal cases. We investigate an under-studied legal domain with a case study on refugee law Canada. Searching case law for past similar cases is a key part of legal work for both lawyers and judges, the potential end-users of our prototype. While traditional named-entity recognition labels such as dates are meaningful information in law, we propose to extend existing models and retrieve a total of 19 categories of items from refugee cases. After creating a novel data set of cases, we perform information extraction based on state-of-the-art neural named-entity recognition (NER). We test different architectures including two transformer models, using contextual and non-contextual embeddings, and compare general purpose versus domain-specific pre-training. The results demonstrate that models pre-trained on legal data perform best despite their smaller size, suggesting that domain-matching had a larger effect than network architecture. We achieve a F1- score superior to 90% on five of the targeted categories and superior to 80% on an additional 4 categories.
%R 10.18653/v1/2023.findings-acl.187
%U https://aclanthology.org/2023.findings-acl.187/
%U https://doi.org/10.18653/v1/2023.findings-acl.187
%P 2992-3005
Markdown (Informal)
[Automated Refugee Case Analysis: An NLP Pipeline for Supporting Legal Practitioners](https://aclanthology.org/2023.findings-acl.187/) (Barale et al., Findings 2023)
ACL