Towards a smooth e-justice: Semantic models and machine learning

Abstract

The dynamic deployment of Information and Communication Technologies in the judicial field, together with the dematerialization of proceedings pushed by e-justice plans, is encouraging the introduction of novel litigation support systems. In this paper we present two innovative systems, JUMAS and eJRM, which take up the challenge of exploiting semantics and machine learning techniques for managing in-court and out-of-court proceedings respectively. JUMAS stems from the homonymous EU research project ended in 2011. It provides not only a streamlined content creation and management support for acquiring and sharing the knowledge embedded into judicial folders, but also a semantic enrichment of multimedia data towards a better usability of judicial folders. eJRM arises from the related ongoing research project funded in the framework PON Ricerca e Competitività 2007-2013. It exploits semantic representation and machine learning reasoning mechanisms towards a support system for online mediation to encourage the resolution of out-of-court disputes and consequently to increase access to justice.