Répondre à des requêtes cliniques PICO

In this paper, we address the issue of answering PICO (Patient/Problem, Intervention, Comparison, Outcome) clinical queries. The contributions of this work include (1) a new document ranking model based on a prioritized aggregation operator that computes the global relevance score based on the relevance estimation of the semantic facet sub-queries and (2) leverages the importance of the facets according to the document and query under evaluation. The effectiveness of our clinical search approach is empirically evaluated using a clinical retrieval collection including 423 queries and more than 1.2 million of medical abstracts from PubMed. The experimental results show that our approach for PICO query answering significantly overpasses state-of-the-art document ranking models. MOTS-CLÉS : RI Médicale, Requêtes Cliniques, Agrégation de scores, Représentation Sémantique