Exploiting association rules and ontology for semantic document indexing

Fatiha Boubekeur, Mohand Boughanem, Lynda Tamine-Lechani

This paper describes a novel approach for document indexing based on the discovery of contextual semantic relations between concepts. The concepts are first extracted from WordNet ontology. Then we propose to extend and to use the association rules technique in order to discover conditional relations between concepts. Finally, concepts and related contextual relations are organized into a conditional graph.

PDF full paper