Frédérik Bilhaut

Learn More
The work presented in this paper concerns Information Retrieval from geographical documents, i.e. documents with a major geographic component. The final aim, in response to an informational query of the user, is to return a ranked list of relevant passages in selected documents, allowing text browsing within them. We consider in this paper the spatial(More)
RÉSUMÉ. Parmi les différentes facettes de la recherche d'information en données textuelles, la recherche d'informations localisées dans l'espace et dans le temps constitue un domaine d'étude à part entière. Celle-ci nécessite en effet, pour l'indexation comme pour la recherche, des analyses linguistiques et des ressources spécifiques. Le projet GéoSem fut(More)
This paper presents the LinguaStream platform, developped to offer an integrated development environment for designing complex natural language processing (NLP) systems. It relies extensively on XML, and demonstrates a practical use of this standard and surrounding ones for NLP, taking particular attention on semantic concerns.
This paper deals with indexation of multi-modal geographic documents by the mean of two constructs: geographic entities, and their semantic relations. These relations concern more specifically contrast or similarity between the entities with regard to the described phenomenon. Geographic entities are retrieved in both text and maps using proper analysis(More)
Current advances in NLP show the need for assembling into complex processing streams, sets of treatments involving a variety of lingustic objects and analysis methods. To achieve this goal, the Linguastream platform offers both a software architecture and a large set of tools: generic analysis models (grammar-based analysers, transducers, projection of(More)
  • 1