Query optimisation using an improved genetic algorithm

Lynda Tamine (1, 2, 3) , Mohand Boughanem (1, 2)

1 IRIT-SIG - Systèmes d’Informations Généralisées
2 UT3 - Université Toulouse III - Paul Sabatier
3 IRIT-IRIS - Recherche d’Information et Synthèse d’Information

This paper presents an approach to intelligent information retrieval based on genetic heuristics. Recent search has shown that applying genetic models for query optimisation improve the retrieval effectiveness. We investigate ways to improve this process by combining genetic heuristics and information retrieval techniques. More precisely, we propose to integrate relevance feedback techniques to perform the genetic operators and the speciation heuristic to solve the relevance multimodality problem. Experiments, with AP documents and queries issued from TREC, showed the effectiveness of our approach. Keywords: Information

Mots clés: Information Retrieval; Genetic Algorithm; Relevance Feedback

Domaines: Recherche d'information [cs.IR]

Lynda Tamine, Mohand Boughanem. Query optimisation using an improved genetic algorithm. 9th International Conference and Knowledge Management (CIKM 2000), ACM Special Interest Group on Management Information Systems; ACM Special Interest Group on Information Retrieval, Nov 2000, Washington, United States. pp.368-373, ⟨10.1145/354756.354842⟩. ⟨hal-00359566⟩