Legal Information Retrieval systems: State-of-the-art and open issues

Abstract

In the last years, the legal domain has been revolutionized by the use of Information and Communication Technologies, producing large amount of digital information. Legal practitioners’ needs, then, in browsing these repositories has required to investigate more efficient retrieval methods, that assume more relevance because digital information is mostly unstructured. In this paper we analyze the state-of-the-art of artificial intelligence approaches for legal domain, focusing on Legal Information Retrieval systems based on Natural Language Processing, Machine Learning and Knowledge Extraction techniques. Finally, we also discuss challenges – mainly focusing on retrieving similar cases, statutes or paragraph for supporting latest cases’ analysis – and open issues about Legal Information Retrieval systems.