Towards an Arabic legal ontology based on documents properties extraction

Legal information presents a need for every citizen of a State subject to the rule of law or for any organization, legal entity recognized as a legal actor with rights and duties. The formalization of law through legal ontologies has proved their increasingly prominent role in representing, processing and retrieving legal information. Based on this knowledge, it is possible to represent and to make inferences about the semantic content of legal documents. This paper investigates the semi-automatic learning of an ontology from Arabic legal documents. We aim to exploit document properties in order to generate concepts and relations of the ontology. Some experiments were conducted in order to evaluate our approach. The initial results seem promising.