Managing legal documents, particularly court judgments, can pose a significant challenge due to the extensive and continuously growing volume of involved data. The IDJ platform proposed in this paper aims to tackle this challenge by providing knowledge-driven services designed to enforce the streamlined management of legal documents. The IDJ platform consists of a set of modules, repositories, and data flows that interoperate to realize service pipelines enforcing legal document analytics and exploration processes based on a combination of Natural Language Processing (NLP), machine learning, and syntactic rules. In the paper, we describe two service pipelines enforcing knowledge-driven processes over legal documents, namely the entity-based document analytics, and the concept-based document exploration. A comprehensive experimentation of the proposed knowledge-based service pipelines in a real scenario is finally provided, by considering a corpus repository of Italian court decisions collected in the framework of the Next Generation UPP (NGUPP) digital justice project.
Streamlining Legal Document Management: A Knowledge-Driven Service Platform / V. Bellandi, S. Castano, S. Montanelli, S. Siccardi. - In: SN COMPUTER SCIENCE. - ISSN 2661-8907. - 6:2(2025), pp. 166.1-166.17. [10.1007/s42979-025-03694-y]
Streamlining Legal Document Management: A Knowledge-Driven Service Platform
V. Bellandi
Primo
;S. CastanoSecondo
;S. MontanelliPenultimo
;S. SiccardiUltimo
2025
Abstract
Managing legal documents, particularly court judgments, can pose a significant challenge due to the extensive and continuously growing volume of involved data. The IDJ platform proposed in this paper aims to tackle this challenge by providing knowledge-driven services designed to enforce the streamlined management of legal documents. The IDJ platform consists of a set of modules, repositories, and data flows that interoperate to realize service pipelines enforcing legal document analytics and exploration processes based on a combination of Natural Language Processing (NLP), machine learning, and syntactic rules. In the paper, we describe two service pipelines enforcing knowledge-driven processes over legal documents, namely the entity-based document analytics, and the concept-based document exploration. A comprehensive experimentation of the proposed knowledge-based service pipelines in a real scenario is finally provided, by considering a corpus repository of Italian court decisions collected in the framework of the Next Generation UPP (NGUPP) digital justice project.File | Dimensione | Formato | |
---|---|---|---|
s42979-025-03694-y (1).pdf
accesso aperto
Descrizione: Original Research
Tipologia:
Publisher's version/PDF
Dimensione
3.04 MB
Formato
Adobe PDF
|
3.04 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.