Exploring Semi-supervised Hierarchical Stacked Encoder for Legal Judgement Prediction

Predicting the judgment of a legal case from its unannotated case facts is a challenging task. The lengthy and non-uniform document structure poses an even greater challenge in extracting information for decision prediction. In this work, we explore and propose a two-level classification mechanism;...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-11
Main Authors: Prasad, Nishchal, Boughanem, Mohand, Taoufiq Dkaki
Format: Article
Language:English
Subjects:
Clustering
Coders
Data processing
Documents
Predictions
Transformers
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Prasad, Nishchal
Boughanem, Mohand
Taoufiq Dkaki
description Predicting the judgment of a legal case from its unannotated case facts is a challenging task. The lengthy and non-uniform document structure poses an even greater challenge in extracting information for decision prediction. In this work, we explore and propose a two-level classification mechanism; both supervised and unsupervised; by using domain-specific pre-trained BERT to extract information from long documents in terms of sentence embeddings further processing with transformer encoder layer and use unsupervised clustering to extract hidden labels from these embeddings to better predict a judgment of a legal case. We conduct several experiments with this mechanism and see higher performance gains than the previously proposed methods on the ILDC dataset. Our experimental results also show the importance of domain-specific pre-training of Transformer Encoders in legal information processing.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2890142977</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2890142977</sourcerecordid><originalsourceid>FETCH-proquest_journals_28901429773</originalsourceid><addsrcrecordid>eNqNikELgjAYQEcQJOV_GHQW5tTUcxgSHQLrLGN-2kw3--ain5-HfkCnB--9FfF4FIVBFnO-Ib61PWOMH1KeJJFH7sVnGgwq3dEKRhVYNwG-lYWGlgpQoHwoKQZazUI-F1loaRpA2hqkF-iWcnZNByPomV4RGiVnZfSOrFsxWPB_3JL9qbgdy2BC83Jg57o3DvWSap7lLIx5nqbRf9cX6rhBFw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2890142977</pqid></control><display><type>article</type><title>Exploring Semi-supervised Hierarchical Stacked Encoder for Legal Judgement Prediction</title><source>Publicly Available Content Database</source><creator>Prasad, Nishchal ; Boughanem, Mohand ; Taoufiq Dkaki</creator><creatorcontrib>Prasad, Nishchal ; Boughanem, Mohand ; Taoufiq Dkaki</creatorcontrib><description>Predicting the judgment of a legal case from its unannotated case facts is a challenging task. The lengthy and non-uniform document structure poses an even greater challenge in extracting information for decision prediction. In this work, we explore and propose a two-level classification mechanism; both supervised and unsupervised; by using domain-specific pre-trained BERT to extract information from long documents in terms of sentence embeddings further processing with transformer encoder layer and use unsupervised clustering to extract hidden labels from these embeddings to better predict a judgment of a legal case. We conduct several experiments with this mechanism and see higher performance gains than the previously proposed methods on the ILDC dataset. Our experimental results also show the importance of domain-specific pre-training of Transformer Encoders in legal information processing.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Clustering ; Coders ; Data processing ; Documents ; Predictions ; Transformers</subject><ispartof>arXiv.org, 2023-11</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by-nc-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2890142977?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Prasad, Nishchal</creatorcontrib><creatorcontrib>Boughanem, Mohand</creatorcontrib><creatorcontrib>Taoufiq Dkaki</creatorcontrib><title>Exploring Semi-supervised Hierarchical Stacked Encoder for Legal Judgement Prediction</title><title>arXiv.org</title><description>Predicting the judgment of a legal case from its unannotated case facts is a challenging task. The lengthy and non-uniform document structure poses an even greater challenge in extracting information for decision prediction. In this work, we explore and propose a two-level classification mechanism; both supervised and unsupervised; by using domain-specific pre-trained BERT to extract information from long documents in terms of sentence embeddings further processing with transformer encoder layer and use unsupervised clustering to extract hidden labels from these embeddings to better predict a judgment of a legal case. We conduct several experiments with this mechanism and see higher performance gains than the previously proposed methods on the ILDC dataset. Our experimental results also show the importance of domain-specific pre-training of Transformer Encoders in legal information processing.</description><subject>Clustering</subject><subject>Coders</subject><subject>Data processing</subject><subject>Documents</subject><subject>Predictions</subject><subject>Transformers</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNikELgjAYQEcQJOV_GHQW5tTUcxgSHQLrLGN-2kw3--ain5-HfkCnB--9FfF4FIVBFnO-Ib61PWOMH1KeJJFH7sVnGgwq3dEKRhVYNwG-lYWGlgpQoHwoKQZazUI-F1loaRpA2hqkF-iWcnZNByPomV4RGiVnZfSOrFsxWPB_3JL9qbgdy2BC83Jg57o3DvWSap7lLIx5nqbRf9cX6rhBFw</recordid><startdate>20231114</startdate><enddate>20231114</enddate><creator>Prasad, Nishchal</creator><creator>Boughanem, Mohand</creator><creator>Taoufiq Dkaki</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231114</creationdate><title>Exploring Semi-supervised Hierarchical Stacked Encoder for Legal Judgement Prediction</title><author>Prasad, Nishchal ; Boughanem, Mohand ; Taoufiq Dkaki</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28901429773</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Clustering</topic><topic>Coders</topic><topic>Data processing</topic><topic>Documents</topic><topic>Predictions</topic><topic>Transformers</topic><toplevel>online_resources</toplevel><creatorcontrib>Prasad, Nishchal</creatorcontrib><creatorcontrib>Boughanem, Mohand</creatorcontrib><creatorcontrib>Taoufiq Dkaki</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Databases</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Prasad, Nishchal</au><au>Boughanem, Mohand</au><au>Taoufiq Dkaki</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Exploring Semi-supervised Hierarchical Stacked Encoder for Legal Judgement Prediction</atitle><jtitle>arXiv.org</jtitle><date>2023-11-14</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Predicting the judgment of a legal case from its unannotated case facts is a challenging task. The lengthy and non-uniform document structure poses an even greater challenge in extracting information for decision prediction. In this work, we explore and propose a two-level classification mechanism; both supervised and unsupervised; by using domain-specific pre-trained BERT to extract information from long documents in terms of sentence embeddings further processing with transformer encoder layer and use unsupervised clustering to extract hidden labels from these embeddings to better predict a judgment of a legal case. We conduct several experiments with this mechanism and see higher performance gains than the previously proposed methods on the ILDC dataset. Our experimental results also show the importance of domain-specific pre-training of Transformer Encoders in legal information processing.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_2890142977
source Publicly Available Content Database
subjects Clustering
Coders
Data processing
Documents
Predictions
Transformers
title Exploring Semi-supervised Hierarchical Stacked Encoder for Legal Judgement Prediction
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T01%3A52%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Exploring%20Semi-supervised%20Hierarchical%20Stacked%20Encoder%20for%20Legal%20Judgement%20Prediction&rft.jtitle=arXiv.org&rft.au=Prasad,%20Nishchal&rft.date=2023-11-14&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2890142977%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_28901429773%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2890142977&rft_id=info:pmid/&rfr_iscdi=true