An adaptive information retrieval system based on associative networks
Helmut Berger, Michael Dittenbach, Dieter Merkl · 2004
In this paper we present a multilingual information retrieval system that provides access to Tourism in-formation by exploiting the intuitiveness of natural language. In particular, we describe the knowledge representation model underlying the information re-trieval system. This knowledge representation ap-proach is based on associative networks and allows the definition of semantic relationships between domain-intrinsic information items. The network structure is used to define weighted associations between in-formation items and augments the system with a fuzzy search strategy. This particular search strat-egy is performed by a constrained spreading activa-tion algorithm that implements information retrieval on associative networks. Strictly speaking, we take the relatedness of terms into account and show, how this fuzzy search strategy yields beneficial results and, moreover, determines highly associated matches to users ’ queries. Thus, the combination of the associa-tive network and the constrained spreading activation approach constitutes a search algorithm that evalu-ates the relatedness of terms and, therefore, provides a means for implicit query expansion.