An extended value-based argumentation framework for ontology mapping with confidence degrees

Abstract

Heuristics to combine different approaches for ontology mapping have been proposed in the literature. This paper proposes to use abstract argumentation frameworks to combine such approaches. We extend the Value-based Argumentation Framework (VAF)[2], in order to represent arguments with confidence degrees. Our agents apply individual mapping algorithms and cooperate in order to exchange their local results (arguments). Next, 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.