Extraction et regroupement de descripteurs morpho-syntaxiques pour des processus de Fouille de Textes

Words are one of the grounds of European languages. Corpora written with these languages are normallydescribe by words. However, extracted information given by words is semantically poor. Actually, totake into account the complexity of European languages are really important. As a result, we propose inthis thesis to feature the characteristic of European languages by using syntactic informations in orderto discover new semantic knowledge from corpora.First, we present SELDE, a model of feature selection. This one is based on objects extracted fromsyntactic relations of a corpus. We experiment SELDE on textual classification tasks by proposing Ex-pLSA, an approach used to make a corpus expansion by using the SELDE features. The goal of ExpLSAis to combine the SELDE features with the statistic method LSA.The SELDE model gives relevant features but cannot be apply with all kinds of textual data. Thus, wepropose different approaches adapted to specific textual data, called complex textual data. We experimentour approaches with noised data, bad written data, and data without syntactic informations.Finally, we propose the SELDEF model. It introduce the automatic validation of syntactic relationscalled induced. Two validation approaches are proposed : a Semantic-Vector-based approach and a WebValidation system. The Semantic Vectors approach is a Roget-based method which computes a syntacticrelation as a vector. Web Validation uses a search engine to determine the relevance of a syntacticrelation. Then, we propose approaches to combine both in order to rank induced syntactic relations.We experiment SELDEF in a conceptual classes building task. Obtained results confirm the quality ofvalidation approaches and quality of built classes. Discipline : Informatique Laboratoire : Laboratoire d’Informatique, de Robotique et de Micro-électronique de Montpellier(LIRMM) ; UMR 5506 ; 161 rue Ada, 34392 Montpellier Cedex 5, France Mots clés : TAL, fouille de textes, descripteur, syntaxe, classification.