Creation, Reuse, Normalisation and Integration of Terminologies in Natural Language Processing Systems

Informations projet

TRANSTERM

N° de convention de subvention: LRE62055

Projet clôturé

Date de début 1 Decembre 1993

Date de fin 1 Decembre 1995

Financé au titre de

• Specific programme of research and technological development (EEC) in the field of telematic systems in areas of general interest - Linguistic research and engineering -, 1990-1994

Coût total € 0,00

Contribution de l’UE Aucune donnée

Coordonné par

GSI-ERLI
France

Résultats exploitables

TRANSTERM: terminologies in natural language processing systems

The project TRANSTERM addresses the problems of enriching terminologies and integrating them into application dictionaries of natural language processing systems. It also addresses problems related to the (re)structuring of existing terminological resources using linguistic knowledge. TRANSTERM also deals with automatic and semi-automatic construction of application terminologies from corpora. TRANSTERM is producing a set of methods and standards (the most important being a unifying model for terminological resources that allows easy linking with GENELEX lexicons) as well as a modular software toolbox enabling users to perform different merging, extraction and update operations. A model has been drafted and is being tested with data from real applications. An accompanying toolbox is currently being implemented (C++, UNIX, OSF/MOTIF).