Langues et domination. Statut social et/ou mélange des genres

Revisiter le couplage traitement automatique des langues et recherche d'information

Information retrieval systems (IRSs) aim at establishing a relationship between users' in-formation needs and the information contained in documents. To this end, a commonly usedmethod consists of making a simple match between query terms and document words. IRSsface two problems with such a mechanism. The rst problem is related to polysemy : a singleterm may have di erent meani...

Bureau Des Traductions Division Des Langues Étrangères

Problématique des chercheurs en traitement automatique des langues des signes

French Sign Language (LSF) automatic processing research has to deal with uncomplete corpora of a language which is not yet fully described and has no written form. So, the researchers must carry out reductions at every representational level, constrain the conditions of acquisition of LSF discourses and limit the field of their applications. It is important that they should explain and justify...

Estimation robuste des modèles de mélange sur des données distribuées

This work proposes a contribution aiming at probabilistic model estimation, in the setting of distributed, decentralized, data-sharing computer systems. Such systems are developing over the internet, and also exist as sensor networks, for instance. Our general goal consists in estimating a probability distribution over a data set which is distributed into subsets located on the nodes of a distr...

Sur le statut référentiel des entités nommées

We show in this paper that, on the one hand, named entities can be designated using different denominations and that, on the second hand, names denoting named entities are polysemous. The analysis cannot be limited to reference resolution but should take into account naming strategies, which are mainly based on two linguistic operations: synecdoche and metonymy. Lastly, we present a model that ...