Legal NLP refers to the application of advanced techniques to processing and analysis of legal texts. In this paper, we present a review of the relevant literature on legal NLP, and we compare existing solutions on four main tasks, that are document segmentation, information retrieval, document summarization, and knowledge extraction. In the review, we focus on how language models are currently being employed for addressing NLP in the legal field, by also highlighting challenges where improvements are still possible.
Language Models for Legal NLP: A Literature Review / A. Abdul Khaliq, S. Montanelli (LECTURE NOTES IN BUSINESS INFORMATION PROCESSING). - In: Advanced Information Systems Engineering Workshops / [a cura di] J. Grabis, Y. Wautelet. - [s.l] : Springer Science and Business Media Deutschland GmbH, 2025 Jun 15. - ISBN 978-3-031-94930-2. - pp. 326-337 (( Intervento presentato al 37. convegno CAiSE tenutosi a Vienna nel 2025 [10.1007/978-3-031-94931-9_27].
Language Models for Legal NLP: A Literature Review
A. Abdul Khaliq
Writing – Original Draft Preparation
;S. MontanelliWriting – Review & Editing
2025
Abstract
Legal NLP refers to the application of advanced techniques to processing and analysis of legal texts. In this paper, we present a review of the relevant literature on legal NLP, and we compare existing solutions on four main tasks, that are document segmentation, information retrieval, document summarization, and knowledge extraction. In the review, we focus on how language models are currently being employed for addressing NLP in the legal field, by also highlighting challenges where improvements are still possible.
| File | Dimensione | Formato | |
|---|---|---|---|
|
978-3-031-94931-9_27.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Licenza:
Nessuna licenza
Dimensione
781.75 kB
Formato
Adobe PDF
|
781.75 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
