Ontology Mapping for a Legal Question Answering System

Abstract

Legal information retrieval systems, such question answering, use legal ontologies to represent semantic objects, to associate them with legal documents and to make inferences about them. The ontology mapping process can help users to reuse and compare information from different ontologies. In this paper we present a review on legal ontologies and present an approach to ontology mapping based on argumentation. Individual mappings are computed by specialized agents using different mapping approaches. Next, these agents use argumentation to exchange their local results, in order to agree on the obtained mappings. To each argument is associated a strength, representing how confident an agent is in the similarity of two ontology terms. Based on their preferences and confidence of the arguments, the agents compute their preferred mapping sets. The arguments in such preferred sets are viewed as the set of globally acceptable arguments. This work is part of a question answering system for the legal domain.