Dominique Dutoit

Learn More
~DLffO1T MEMODATA 23 rmdesaoufi~ 14000 Ca~ Frm~ RESUME UNE APPRO~tE ENSEMBLtSIE DU ~ ~ r,bus pr~ntms ~ ~a~ts d'm travan mm~ depuis ltt~mrs ~ par la sooi(~ ~DATA stria ~ s~mmtique du lexique ~ Ce travail a fait l'objet d'tm lmm~ ~ & ~ av~ le ~& h ~a delaT~ et ab(x~ attjourd'hui ~ un diaimrtm k~id de #us de ~mmo Le fitr¢ "dk~tm~ amiog~" lcgro~ des r6ali~s(More)
This paper presents a module dedicated to the elaboration of linguistic resources for a versatile Information Extraction system. In order to decrease the time spent on the elaboration of resources for the IE system and guide the end-user in a new domain, we suggest to use a machine learning system that helps defining new templates and associated resources.(More)
This paper evaluates two different approaches for the elaboration of semantic classes. The framework is an Information Extraction, which needs large amount of domain-dependent resources. An endogenous approach (corpus-based learning) is contrasted with a heterogeneous one (the use of a large semantic network). The two techniques are evaluated. Cet article(More)
This paper presents a system to find automatically words from a definition or a paraphrase. The system uses a lexical database of French words that is comparable in its size to WordNet and an algorithm that evaluates distances in the semantic graph between hy-pernyms and hyponyms of the words in the definition. The paper first outlines the structure of the(More)
The semantic organization of the web is one the major challenges for the future of the Internet. This important task may be based on the development of new approaches, taking the risk of reinventing the wheel, or may consider the previous efforts and successes, offering the opportunity to move research to market. This paper is a technical study that(More)