User models and domain ontologies for generating personalized questions and answers

Abstract

The incorporation of user models has become more popular in recent years. This paper describes how user models, domain ontologies and natural language generation techniques can be integrated to generate personalized questions and answers related to a particular scenario. For this purpose, a general organization of different types of knowledge involved is proposed, that facilitates its adaptation to different domains, user models and languages. In this proposal, the domain conceptual knowledge is represented by a domain ontology, that provides a framework for representing the user’s knowledge and interests. Ontologies provide a powerful formalism because they allow the representation of detailed descriptions of concepts, attributes and relations, thus facilitating richer inferences about user knowledge and interests. Additionally, in the approach presented, the domain concepts in the ontology are also related to a general syntactic-semantic taxonomy that facilitates the generation of more appropriate questions and answers for each user. The proposed organization has been applied for generating personalized questions and answers, that help the user when searching information about university courses.