TULSI: an NLP system for extracting legal modificatory provisions

• Published in: Artificial intelligence and law Vol. 21; no. 2; pp. 139 - 172
• Main Authors: Lesmo, Leonardo, Mazzei, Alessandro, Palmirani, Monica, Radicioni, Daniele P.
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.05.2013; Springer; Springer Nature B.V
• Subjects: Analysis; Annotations; Applied sciences; Artificial Intelligence; Automatic abstracting; Computational linguistics; Computer Science; Computer science; control theory; systems; Documents; Exact sciences and technology; Expert systems; Extraction; General aspects; Information processing; Information Storage and Retrieval; Information systems. Data bases; Intellectual Property; Interpreters; IT Law; Language processing; Law; Laws, regulations and rules; Legal; Legal Aspects of Computing; Legislation. Standardization; Media Law; Memory organisation. Data processing; Natural language interfaces; Natural language processing; Philosophy of Law; Semantic analysis; Semantics; Software; Speech and sound recognition and synthesis. Linguistics; Studies; Italy; Semantic interpretation; Natural language processing; Information extraction; Law; Interpreter; Language processing; University; Semantics; Legislation; Syntactic analysis; Natural language; Annotation
• ISSN: 0924-8463; 1572-8382
• DOI: 10.1007/s10506-012-9127-6

In this work we present the TULSI system (so named after Turin University Legal Semantic Interpreter), a system to produce automatic annotations of normative documents through the extraction of modificatory provisions. TULSI relies on a deep syntactic analysis and a shallow semantic interpreter that are illustrated in detail. We report the results of an experimental evaluation of the system and discuss them, also suggesting future directions for further improvement.