Automatic Construction of a TMF Terminological Database using a Transducer Cascade

The automatic development of terminological databases, especially in a standardized format, has a crucial aspect for multiple applications related to technical and scientific knowledge that requires semantic and terminological descriptions covering multiple domains. In this context, we have, in this paper, two challenges: the first is the automatic extraction of terms in order to build a terminological database, and the second challenge is their normalization into a standardized format. To deal with these challenges, we propose an approach based on a cascade of transducers performed using CasSys tool of the Unitex linguistic platform that benefits from both: the success of the rule-based approach for the extraction of terms, and the performance of the TMF standard for the representation of terms. We have tested and evaluated our approach on an Arabic scientific and technical corpus for the Elevator domain and the results are very encouraging.