Bhupatiraju, Sandeep, Chen, Daniel L. and Venkataramanan, Kannan (2024) Mapping the Geometry of Law Using Natural Language Processing. European Journal of Empirical Legal Studies, vol. 1 (n° 1). pp. 49-68.

This is the latest version of this item.

Full text not available from this repository.
Identification Number : 10.62355/ejels.18073

Abstract

Judicial documents and judgments are a rich source of information about legal cases, litigants, and judicial decision-makers. Natural language processing (NLP) based approaches have recently received much attention for their ability to decipher implicit information from text. NLP researchers have successfully developed data-driven representations of text using dense vectors that encode the relations between those objects. In this study, we explore the application of the Doc2Vec model to legal language to understand judicial reasoning and identify implicit patterns in judgments and judges. In an application to federal appellate courts, we show that these vectors encode information that distinguishes courts in time and legal topics. We use Doc2Vec document embeddings to study the patterns and train a classifier model to predict cases with a high chance of being appealed at the Supreme Court of the United States (SCOTUS). There are no existing benchmarks, and we present the first results at this task at scale. Furthermore, we analyze generic writing/judgment patterns of prominent judges using deep learning-based autoencoder models. Overall, we observe that Doc2Vec document embeddings capture important legal information and are helpful in downstream tasks.

Item Type: Article
Language: English
Date: 13 May 2024
Refereed: Yes
Uncontrolled Keywords: Natural language processing, Legal language, Judicial reasoning, Judicial behavior, Embeddings
Subjects: B- ECONOMIE ET FINANCE
Divisions: TSE-R (Toulouse)
Site: UT1
Date Deposited: 19 Dec 2024 08:48
Last Modified: 07 Jan 2025 10:13
OAI Identifier: oai:tse-fr.eu:129304
URI: https://publications.ut-capitole.fr/id/eprint/49335

Available Versions of this Item

View Item