Treffer: Linking Appellate Judgments to Tribunal Judgments – Benchmarking Different ML Techniques
Title:
Linking Appellate Judgments to Tribunal Judgments – Benchmarking Different ML Techniques
Authors:
Contributors:
Détection, évaluation, gestion des risques CHROniques et éMErgents (CHROME) - Nîmes Université (CHROME), Nîmes Université (UNIMES), Centre Européen de Droit et d'Economie (CEDE), ESSEC Business School, Enrico Francesconi, Georg Borges, Christoph Sorge, ANR-20-CE38-0013,LAWBOT,APPRENTISSAGE PROFOND POUR LA MODELISATION PREDICTIVE DE LA JURISPRUDENCE(2020)
Source:
Enrico Francesconi; Georg Borges; Christoph Sorge. Legal Knowledge and Information Systems. :33-42
Publisher Information:
CCSD; IOS Press, 2022.
Publication Year:
2022
Collection:
collection:SHS
collection:ESSEC
collection:AO-DROIT
collection:UNIMES
collection:ANR
collection:ESSEC
collection:AO-DROIT
collection:UNIMES
collection:ANR
Subject Terms:
Legal document linking, Document similarity, Long document processing, Named entity recognition, Siamese network, [INFO.INFO-TT]Computer Science [cs], Document and Text Processing, [INFO.INFO-AI]Computer Science [cs], Artificial Intelligence [cs.AI], [SHS.DROIT]Humanities and Social Sciences, Law, [STAT.ML]Statistics [stat], Machine Learning [stat.ML]
Original Identifier:
HAL: hal-04546611
Document Type:
Buch
bookPart<br />Book sections
Language:
English
ISBN:
978-1-64368-364-5
Relation:
info:eu-repo/semantics/altIdentifier/doi/10.3233/FAIA220446
DOI:
10.3233/FAIA220446
Access URL:
Rights:
info:eu-repo/semantics/OpenAccess
URL: http://creativecommons.org/licenses/by-nc/
URL: http://creativecommons.org/licenses/by-nc/
Accession Number:
edshal.hal.04546611v1
Database:
HAL
Weitere Informationen
The typical judicial pathway is made of a judgment by a tribunal followed by a decision of an appellate court. However, the link between both documents is sometimes difficult to establish because of missing, incorrect or badly formatted references, pseudonymization, or poor drafting specific to each jurisdiction. This paper first shows that it is possible to link court decisions related to the same case although they are from different jurisdictions using manual rules. The use of deep learning afterwards significantly reduces the error rate in this task. The experiments are conducted between the Commercial Court of Paris and Appellate Courts.