inria-00107805, version 1
Construction of Grammar Based Term Extraction Model for Japanese
Koichi Takeuchi a, 1Kyo Kageura b, 2Teruo Koyama c, 2Béatrice Daille d, 3Laurent Romary
e, 4
3rd International Workshop on Computational Terminology - CompuTerm 2004 (2004) 91-94
Résumé : In this paper we propose a grammar-based term extraction model for Japanese toward construction of multilingual term dictionary. The proposed approach evaluates termhood using morphological patterns of terms. Most of terms in Japanese consist of compound nouns or simple phrases, but detailed grammatical patterns for term extraction have not been constructed because of their complex compounding mechanisms. Applying detailed morphological investigation to Japanese compounding, we make sure their structures of word formation that can be comparable to those of Indo-European terms such as English and French.
- a – OKAYAMA UNIVERSITY
- b – NATIONAL INSTITUTE OF INFORMATICS
- c – NATIONAL INSTITUTE OF INFORMATICS - TOKYO
- d – IRIN - UNIVERSITE DE NANTES
- e – INRIA
- 1 : Faculty of Engineering
- Okayama University
- 2 : National Institute of Informatics [Tokyo] (NII)
- National Institute of Informatics
- 3 : Laboratoire d'Informatique de Nantes Atlantique (LINA)
- CNRS : UMR6241 – Université de Nantes – Ecole des Mines de Nantes
- 4 : LANGUE ET DIALOGUE (INRIA Lorraine - LORIA)
- INRIA – CNRS : UMR7503 – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL)
- Domaine : Informatique/Informatique et langage
- Référence interne : A04-R-534 || takeuchi04a
- Commentaire : Colloque avec actes et comité de lecture. internationale.
- inria-00107805, version 1
- http://hal.inria.fr/inria-00107805
- oai:hal.inria.fr:inria-00107805
- Contributeur : Laurent Romary
- Soumis le : Mardi 14 Juillet 2009, 14:56:49
- Dernière modification le : Jeudi 16 Juillet 2009, 09:15:12






Documents associés
Exporter