Using a Medical Thesaurus to Predict Query Difficulty

Florian Boudin (1) , Jian-Yun Nie (2) , Martin Dawes (3)

1 LS2N - équipe TALN - Traitement Automatique du Langage Naturel
2 RALI - Recherche appliquée en linguistique informatique
3 UBC - University of British Columbia

Estimating query performance is the task of predicting the quality of results returned by a search engine in response to a query. In this paper, we focus on pre-retrieval prediction methods for the medical domain. We propose a novel predictor that exploits a thesaurus to as- certain how difficult queries are. In our experiments, we show that our predictor outperforms the state-of-the-art methods that do not use a thesaurus.

Domaines: Traitement du texte et du document

Florian Boudin, Jian-Yun Nie, Martin Dawes. Using a Medical Thesaurus to Predict Query Difficulty. 34th European Conference on Information Retrieval (ECIR), Apr 2012, Barcelone, Spain. pp.480-484. ⟨hal-00707691⟩