Automatically Populating Acception Lexical Database through Bilingual Dictionaries and Conceptual Vectors

The NLP team of LIRMM currently works on thematic and lexical disambiguation text analysis [Lafourcade, 2001]. We built a system, with automated learning capabilities, based on conceptual vectors for meaning representation. Vectors are supposed to encode ideas associated to words or expressions. In the framework of Acception Based Lexical Database (instantiated through the Papillon project), we devise some conceptual vector based strategies to automatically populate and check acceptions. In this context, an acception represents a meaning of an entry of a monolingual dictionary, and could be refined and associated to a conceptual vector. Vectors are used for decision making and link quality assessment.