The management of legal documents, especially court judgments, can be a daunting task due to the vast amounts of data involved. Traditional methods of managing legal documents are no longer sufficient, as the volume of data continues to increase, leading to the need for more advanced and efficient systems. The proposed infrastructure seeks to address this challenge by organizing a repository of textual documents and annotating them in a way that facilitates various downstream tasks. The framework is designed to be developed and maintained in a sustainable way, ensuring multiple services and uses of the annotated document repository while considering the limited availability of annotated data. This approach ensures that the output of the annotation algorithms aligns with the organizational processes used in Italian courts. The experiments conducted to demonstrate the feasibility of the solution employed different low-resource methods and solutions designed to combine these approaches in a meaningful way.

A Service Infrastructure for the Italian Digital Justice / V. Bellandi, S. Castano, S. Montanelli, D. Riva, S. Siccardi (COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE). - In: Management of Digital EcoSystems / [a cura di] R. Chbeir, D. Benslimane, M. Zervakis, Y. Manolopoulos, N. Thanh Ngyuen, J. Tekli. - [s.l] : Springer Science, 2024. - ISBN 9783031516429. - pp. 179-192 (( Intervento presentato al 15. convegno MEDES tenutosi a Heraklion nel 2023 [10.1007/978-3-031-51643-6_13].

A Service Infrastructure for the Italian Digital Justice

V. Bellandi
;
S. Castano
;
S. Montanelli
;
D. Riva;S. Siccardi
2024

Abstract

The management of legal documents, especially court judgments, can be a daunting task due to the vast amounts of data involved. Traditional methods of managing legal documents are no longer sufficient, as the volume of data continues to increase, leading to the need for more advanced and efficient systems. The proposed infrastructure seeks to address this challenge by organizing a repository of textual documents and annotating them in a way that facilitates various downstream tasks. The framework is designed to be developed and maintained in a sustainable way, ensuring multiple services and uses of the annotated document repository while considering the limited availability of annotated data. This approach ensures that the output of the annotation algorithms aligns with the organizational processes used in Italian courts. The experiments conducted to demonstrate the feasibility of the solution employed different low-resource methods and solutions designed to combine these approaches in a meaningful way.
Concept Extraction; Legal Document Annotation; Named Entity Recognition; Zero-Shot Learning
Settore INF/01 - Informatica
2024
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
978-3-031-51643-6_13.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 969.52 kB
Formato Adobe PDF
969.52 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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/1053448
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact