Indexing biomedical documents with a possibilistic network

We propose in this paper a new approach for indexing biomedical documents based on a possibilistic network, which carries out partial matching between documents and biomedical vocabulary. The main contribution of our approach is to deal with the imprecision and uncertainty of the indexing task using possibility theory. We aim to enhance estimation of the similarity between a document and a given concept using the two measures of possibility and necessity. Possibility estimates the extent to which a document is not similar to the concept. The second allows confirmation that the document is similar to the concept. Our contribution also consists in reducing the limitation of partial matching. Although this latter allows extracting from the document other variants of terms than those in dictionaries, it also generates irrelevant information. Our objective is to filter the index using the knowledge provided by the Unified Medical Language System® (UMLS). Experiments were carried out on different corpus, showing very encouraging results (the improvement rate is +26.82% in terms of Main Average Precision compared to baseline).