DOCUMENT CONTENT MODELS

The Document Content Models research explores formalisms and techniques for specifying, manipulating and exploiting the semantic structures of documents, seen as global, cohesive, objects. Document representations focus on high-level communicative goals; they are specified through constraint mechanisms which may involve interaction with external knowledge bases. Applications include controlled authoring, interactive generation, natural language interfaces, global document content analysis, document normalization.

CURRENTS PROJECTS

Multilingual Document Authoring

The MDA (Multilingual Document Authoring) project provides interactive tools, such as context-aware menus, for assisting monolingual writers in the production of multilingual documents.
MDA factsheet- MDA demo video available

Document Normalization

Document Normalization is the interactive process of legacy document analysis into some well-defined and controlled document content model and the generation of a corresponding normalized document.

PUBLICATIONS

Caroline Brun, Marc Dymetman, Veronika Lux, Document Structure and Multilingual Text Authoring, in the Proceedings of INLG'2000, Mitzpe Ramon, Israel, 2000 (PDF - PS)

Marc Dymetman, Veronika Lux, Aarne Ranta, XML and Multilingual Document Authoring: Converging Trends, in the Proceedings of COLING'2000, Saarbrucken, Germany, 2000 (PDF - PS)

Aurélien Max, Marc Dymetman, Document Content Analysis through Fuzzy Inverted Generation, in AAAI 2002 Spring Symposium on Using (and Acquiring) Linguistic (and World) Knowledge for Information Access, Stanford University, United States, 2002 (PDF)

Marc Dymetman, Document Content Authoring and Hybrid Knowledge Bases, in the Proceedings of KRDB-02 (Knowledge Representation meets Knowledge Bases), Toulouse, France, 2002 (PDF)

Aurélien Max, Normalisation de Documents par Analyse du Contenu à l'Aide d'un Modèle Sémantique et d'un Générateur, in the Proceedings of TALN-RECITAL 2002, Nancy, France, 2002 (PDF)

Marc Dymetman, Text Authoring, Knowledge Acquisition and Description Logics, in the Proceedings of COLING-02, Taiwan, August 2002 (PDF - PS)

Caroline Brun, Marc Dymetman, Rédaction Multilingue Assistée dans le Modèle MDA, in Multilinguisme et Traitement de l'Information, Frédérique Segond ed., Hermès, Paris 2002 (book description)