Automatic Construction of a TMF Terminological Database using a Transducer Cascade

Proceedings of Recent Advances in Natural Language Processing, pages 17–23, Hissar, Bulgaria, Sep 7–9 2015. Automatic Construction of a TMF Terminological Database Using a Transducer Cascade Chihebeddine Ammar MIRACL & Sfax University Sfax, Tunisia chihebeddine.ammar@fss.rnu.tn Kais Haddar MIRACL & Sfax University Sfax, Tunisia kais.haddar@fss.rnu.tn Laurent Romary INRIA & Humboldt University Berlin, Germany laurent.romary@inria.fr Abstract The automatic development of termino- logical databases, especially in a standard- ized format, has a crucial aspect for mul- tiple applications related to technical and scientific knowledge that requires seman- tic and terminological descriptions cover- ing 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 normal- ization into a standardized format. To deal with these challenges, we propose an ap- proach based on a cascade of transducers performed using CasSys tool of the Uni- tex linguistic platform that benefits from both: the success of the rule-based ap- proach 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 El- evator domain and the results are very en- couraging. 1 Introduction The automation of terminology will reduce the time and cost that usually takes terminological database construction. It will also help us to con- struct terminological databases with broad cover- age, especially for recent concepts and poor lan- guage coverage (Arabic for example). On the other side, the representation of terminological data in a standard format allows the integration and merging of terminological data from multi- ple source systems, while improving terminolog- ical data quality and maintaining maximum inter- operability between different applications. One of the very rich in terminology working area are the scientific and technical documents. They cover several scientific and technical fields, so, we will need several terminological databases, one for each field. For this reason, we decided to work on a specific domain: the elevators. To automate any process, we need a framework. The choice of this framework is not an easy task. In fact, many frameworks exist, based on: formal grammars, logical formalism, discrete mathemat- ics, etc. The rule-based approach requires: a thor- ough study of the characteristics of terms and con- struction of necessary resources such as dictionar- ies, trigger words and extraction rules. Finite automata and in particularly transducers are often used in the Natural Language Process- ing (NLP). The general idea is to replace the rules of formal grammars with representation forms. Transducers offer a particularly nice and simple formulation, and prove their capability of repre- senting complex grammars due to their graphic representation. They have a success for the extrac- tion of named entities (NE) and terms. In fact, pre- cision is more important for rule-based systems. Another issue is to decide which standard will we choose to model our terminological databases, which standard will best represent scientific and technical terms …

Content truncated to 500 words