Abstract de la publi numéro 13024

In the context of document retrieval in the biomedical domain, this paper introduces a novelapproach to searching for biomedical information using contextual semantic information. Morespecifically, we propose to combine the contextual semantic information in documents and userqueries in an attempt to improve the performance of biomedical information retrieval (IR) systems.Contextual information provides knowledge about a domain in a global context or statistical propertiesof a sub collection of documents related to a given query in a local context.In our context sensitive IR approach, terms denoting concepts are extracted from each document usingseveral biomedical terminologies. Preferred terms denoting concepts are used to enrich the semanticsof the document content via document expansion. The user query is expanded using terms extractedfrom the top-ranked expanded documents via a blind feedback query expansion approach. In addition,we aim to evaluate the utility of incorporating several terminologies within the proposed contextsensitive approach. The experiments carried out on the TREC Genomics 2004 and 2005 test sets showthat our context-sensitive IR approach significantly outperforms state-of-the-art baseline approaches.