Enhancing Pre-Trained Language Models with Sentence Position Embeddings for Rhetorical Roles Recognition in Legal Opinions - Archive ouverte HAL
Conference Papers Year : 2023

Enhancing Pre-Trained Language Models with Sentence Position Embeddings for Rhetorical Roles Recognition in Legal Opinions

Abstract

The legal domain is a vast and complex field that involves a considerable amount of text analysis, including laws, legal arguments, and legal opinions. Legal practitioners must analyze these texts to understand legal cases, research legal precedents, and prepare legal documents. The size of legal opinions continues to grow, making it increasingly challenging to develop a model that can accurately predict the rhetorical roles of legal opinions given their complexity and diversity. In this research paper, we propose a novel model architecture for automatically predicting rhetorical roles using pre-trained language models (PLMs) enhanced with knowledge of sentence position information within a document. Based on an annotated corpus from the LegalEval@SemEval2023 competition, we demonstrate that our approach requires fewer parameters, resulting in lower computational costs when compared to complex architectures employing a hierarchical model in a global-context, yet it achieves great performance. Moreover, we show that adding more attention to a hierarchical model based only on BERT in the local-context, along with incorporating sentence position information, enhances the results.
Fichier principal
Vignette du fichier
ASAIL2023-no-editor.pdf (306.25 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

hal-04138121 , version 1 (29-06-2023)

Licence

Identifiers

  • HAL Id : hal-04138121 , version 1

Cite

Anas Belfathi, Nicolas Hernandez, Laura Monceaux. Enhancing Pre-Trained Language Models with Sentence Position Embeddings for Rhetorical Roles Recognition in Legal Opinions. 6th Workshop on Automated Semantic Analysis of Information in Legal Text (ASAIL) held online in conjunction with 19th International Conference on Artificial Intelligence and Law (ICAIL), Jun 2023, Braga, Universidad do Minho,, Portugal. ⟨hal-04138121⟩
109 View
43 Download

Share

More