V. Claveau > Publications > I3 journal article Abstract OLST Version française Fabienne Moreau, Vincent Claveau, Extension de requêtes par relations morphologiques acquises automatiquement, Revue I3 (Information - Interaction - Intelligence), Cépaduès éditions, Vol. 6, No 2, p. 31-50, 2006, Document (pdf) Abstract Information retrieval systems (IRS) usually suffer from a low ability to recognize a same idea or concept that is expressed in different forms. A way of improving these systems is to take into account morphological variations. In this paper, we propose a simple method to recognize these variations that are further used so as to enrich queries. In comparison with already published methods, this system does not need an external ressources or knowledge and thus supports many languages. This approach is evaluated on several collections, 6 different languages and compared to existing tools (stemmer, lemmatizer); reported results show a significant improvement of the overall IRS performance in every case.