Legal modeling and automated reasoning with ON-LINE

In this paper we present a modeling approach to legal knowledge systems and its computational realization in the ON-LINE architecture. ON-LINE has mod ules for modeling legal sources, for storing and retrieving legal informati on and for reasoning with legal knowledge. The approach takes two perspecti ves: domain and task. In the domain perspective, a core ontology divides le gal knowledge into five major categories: normative, world, responsibility, reactive and creative. For the normative knowledge, which is most typical of legal domains, we developed a new representation and inference formalism s which are an alternative to deontic logic. For the world knowledge, we ar gue for using a terminological knowledge representation language. The struc ture of the ontology is not a taxonomy, but a network of dependencies betwe en the categories. These dependencies reflect the global structure of argum ents in legal reasoning. In the task perspective, we followed a top-down ap proach using the CommonKADS modeling library. Design, planning and assessme nt were identified as typical tasks in the legal domain. For assessment, a model was specified and implemented. (C) 1999 Academic Press.