E-Gen : traitement automatique d'informations de ressources humaines

Internet is at the heart of the labor market and its use spreads as increase the number of Internet users in the population. Seeking employment through "electronic employment bursary" and e-recruitment has become something current. This information explosion poses various problems in their processing with the large amount of information difficult to manage quickly and effectively. We present in this work the E-Gen project, that analyses and integrates the ads. Based on classifiers systems driven by a Markov automate, the system gets very good results. Thereafter, we present several strategies based on vectorial and probabilistic models to solve the problem of profiling candidates according to a specific ads to assist recruiters. Relevance feedback approach allows to surpass our previous results on this task. MOTS-CLÉS : Traitement Automatique du Langage Naturel Ecrit, Apprentissage Automatique, Recherche d’Information, Ressources humaines, modèles probabilistes, mesures de similarité.