No Cover Image

Journal article 48 views

DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents

Paheli Bhattacharya, Shounak Paul, Kripabandhu Ghosh, Saptarshi Ghosh, Adam Wyner Orcid Logo

Artificial Intelligence and Law, Volume: 31, Issue: 1, Pages: 53 - 90

Swansea University Author: Adam Wyner Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1007/s10506-021-09304-5

Abstract

The task of rhetorical role labeling is to assign labels (such as Fact, Argument, Final Judgement, etc.) to sentences of a court case document. Rhetorical role labeling is an important problem in the field of Legal Analytics, since it can aid in various downstream tasks as well as enhances the reada...

Full description

Published in: Artificial Intelligence and Law
ISSN: 0924-8463 1572-8382
Published: Springer Science and Business Media LLC 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65652
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-02-19T11:53:47Z
last_indexed 2024-02-19T11:53:47Z
id cronfa65652
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>65652</id><entry>2024-02-19</entry><title>DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents</title><swanseaauthors><author><sid>51fa34a3136b8e81fc273fce73e88099</sid><ORCID>0000-0002-2958-3428</ORCID><firstname>Adam</firstname><surname>Wyner</surname><name>Adam Wyner</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-02-19</date><deptcode>SCS</deptcode><abstract>The task of rhetorical role labeling is to assign labels (such as Fact, Argument, Final Judgement, etc.) to sentences of a court case document. Rhetorical role labeling is an important problem in the field of Legal Analytics, since it can aid in various downstream tasks as well as enhances the readability of lengthy case documents. The task is challenging as case documents are highly various in structure and the rhetorical labels are often subjective. Previous works for automatic rhetorical role identification (i) mainly used Conditional Random Fields over manually handcrafted features, and (ii) focused on certain law domains only (e.g., Immigration cases, Rent law), and a particular jurisdiction/country (e.g., US, Canada, India). In this work, we improve upon the prior works on rhetorical role identification by proposing novel Deep Learning models for automatically identifying rhetorical roles, which substantially outperform the prior methods. Additionally, we show the effectiveness of the proposed models over documents from five different law domains, and from two different jurisdictions—the Supreme Court of India and the Supreme Court of the UK. Through extensive experiments over different variations of the Deep Learning models, including Transformer models based on BERT and LegalBERT, we show the robustness of the methods for the task. We also perform an extensive inter-annotator study and analyse the agreement of the predictions of the proposed model with the annotations by domain experts. We find that some rhetorical labels are inherently hard/subjective and both law experts and neural models frequently get confused in predicting them correctly.</abstract><type>Journal Article</type><journal>Artificial Intelligence and Law</journal><volume>31</volume><journalNumber>1</journalNumber><paginationStart>53</paginationStart><paginationEnd>90</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0924-8463</issnPrint><issnElectronic>1572-8382</issnElectronic><keywords>Rhetorical role labeling; Legal document segmentation; Court case documents; Hierarchical BiLSTM; Hierarchical BiLSTM CRF; BERT; LegalBERT</keywords><publishedDay>1</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-03-01</publishedDate><doi>10.1007/s10506-021-09304-5</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>The research is partially supported by SERB, Government of India, through a project titled “NYAYA: A Legal Assistance System for Legal Experts and the Common Man in India” and the TCG Centres for Research and Education in Science and Technology (CREST) through a project titled “Smart Legal Consultant: AI-based Legal Analytics”. P. Bhattacharya is supported by a Fellowship from Tata Consultancy Services.</funders><projectreference/><lastEdited>2024-04-03T14:08:51.8261022</lastEdited><Created>2024-02-19T11:38:18.6302016</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Paheli</firstname><surname>Bhattacharya</surname><order>1</order></author><author><firstname>Shounak</firstname><surname>Paul</surname><order>2</order></author><author><firstname>Kripabandhu</firstname><surname>Ghosh</surname><order>3</order></author><author><firstname>Saptarshi</firstname><surname>Ghosh</surname><order>4</order></author><author><firstname>Adam</firstname><surname>Wyner</surname><orcid>0000-0002-2958-3428</orcid><order>5</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling v2 65652 2024-02-19 DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents 51fa34a3136b8e81fc273fce73e88099 0000-0002-2958-3428 Adam Wyner Adam Wyner true false 2024-02-19 SCS The task of rhetorical role labeling is to assign labels (such as Fact, Argument, Final Judgement, etc.) to sentences of a court case document. Rhetorical role labeling is an important problem in the field of Legal Analytics, since it can aid in various downstream tasks as well as enhances the readability of lengthy case documents. The task is challenging as case documents are highly various in structure and the rhetorical labels are often subjective. Previous works for automatic rhetorical role identification (i) mainly used Conditional Random Fields over manually handcrafted features, and (ii) focused on certain law domains only (e.g., Immigration cases, Rent law), and a particular jurisdiction/country (e.g., US, Canada, India). In this work, we improve upon the prior works on rhetorical role identification by proposing novel Deep Learning models for automatically identifying rhetorical roles, which substantially outperform the prior methods. Additionally, we show the effectiveness of the proposed models over documents from five different law domains, and from two different jurisdictions—the Supreme Court of India and the Supreme Court of the UK. Through extensive experiments over different variations of the Deep Learning models, including Transformer models based on BERT and LegalBERT, we show the robustness of the methods for the task. We also perform an extensive inter-annotator study and analyse the agreement of the predictions of the proposed model with the annotations by domain experts. We find that some rhetorical labels are inherently hard/subjective and both law experts and neural models frequently get confused in predicting them correctly. Journal Article Artificial Intelligence and Law 31 1 53 90 Springer Science and Business Media LLC 0924-8463 1572-8382 Rhetorical role labeling; Legal document segmentation; Court case documents; Hierarchical BiLSTM; Hierarchical BiLSTM CRF; BERT; LegalBERT 1 3 2023 2023-03-01 10.1007/s10506-021-09304-5 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University The research is partially supported by SERB, Government of India, through a project titled “NYAYA: A Legal Assistance System for Legal Experts and the Common Man in India” and the TCG Centres for Research and Education in Science and Technology (CREST) through a project titled “Smart Legal Consultant: AI-based Legal Analytics”. P. Bhattacharya is supported by a Fellowship from Tata Consultancy Services. 2024-04-03T14:08:51.8261022 2024-02-19T11:38:18.6302016 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Paheli Bhattacharya 1 Shounak Paul 2 Kripabandhu Ghosh 3 Saptarshi Ghosh 4 Adam Wyner 0000-0002-2958-3428 5
title DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents
spellingShingle DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents
Adam Wyner
title_short DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents
title_full DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents
title_fullStr DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents
title_full_unstemmed DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents
title_sort DeepRhole: deep learning for rhetorical role labeling of sentences in legal case documents
author_id_str_mv 51fa34a3136b8e81fc273fce73e88099
author_id_fullname_str_mv 51fa34a3136b8e81fc273fce73e88099_***_Adam Wyner
author Adam Wyner
author2 Paheli Bhattacharya
Shounak Paul
Kripabandhu Ghosh
Saptarshi Ghosh
Adam Wyner
format Journal article
container_title Artificial Intelligence and Law
container_volume 31
container_issue 1
container_start_page 53
publishDate 2023
institution Swansea University
issn 0924-8463
1572-8382
doi_str_mv 10.1007/s10506-021-09304-5
publisher Springer Science and Business Media LLC
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 0
active_str 0
description The task of rhetorical role labeling is to assign labels (such as Fact, Argument, Final Judgement, etc.) to sentences of a court case document. Rhetorical role labeling is an important problem in the field of Legal Analytics, since it can aid in various downstream tasks as well as enhances the readability of lengthy case documents. The task is challenging as case documents are highly various in structure and the rhetorical labels are often subjective. Previous works for automatic rhetorical role identification (i) mainly used Conditional Random Fields over manually handcrafted features, and (ii) focused on certain law domains only (e.g., Immigration cases, Rent law), and a particular jurisdiction/country (e.g., US, Canada, India). In this work, we improve upon the prior works on rhetorical role identification by proposing novel Deep Learning models for automatically identifying rhetorical roles, which substantially outperform the prior methods. Additionally, we show the effectiveness of the proposed models over documents from five different law domains, and from two different jurisdictions—the Supreme Court of India and the Supreme Court of the UK. Through extensive experiments over different variations of the Deep Learning models, including Transformer models based on BERT and LegalBERT, we show the robustness of the methods for the task. We also perform an extensive inter-annotator study and analyse the agreement of the predictions of the proposed model with the annotations by domain experts. We find that some rhetorical labels are inherently hard/subjective and both law experts and neural models frequently get confused in predicting them correctly.
published_date 2023-03-01T14:08:48Z
_version_ 1795319113687498752
score 11.012678

Similar Items