This paper addresses the problem of learning to classify texts by exploiting information derived from both training and testing sets. To accomplish this, clustering is used as a complementary step to text classification, and is applied not only to the training set but also to the testing set. This approach allows us to estimate the location of the testing examples and the structure of the whole...

Les systèmes de recherche d'information préconisent une fonctionnalité très intéressante voire indispensable lors de tout processus de recherche : il s'agit de la reformulation automatique de la requête. Cette fonctionnalité permet de rétablir les choix de l'utilisateur dans la perspective de retrouver plus de documents qui répondent à son besoin en information. Il est à noter à ce niveau que l...

We examine the impact on classification effectiveness of semantic differences in categories. Specifically, we measure broadness and narrowness of categories in terms of their distance to the root of a hierarchically organized thesaurus. Using categories of four different levels degrees of broadness, we show that classifying documents into narrow categories gives better scores than classifying t...