Construction of Grammar Based Term Extraction Model for Japanese

Koichi Takeuchi 1 Kyo Kageura 2 Teruo Koyama 2 Béatrice Daille 3 Laurent Romary 4
1 Faculty of Engineering
2 NII - National Institute of Informatics
3 LINA - Laboratoire d'Informatique de Nantes Atlantique
4 LANGUE ET DIALOGUE - Human-machine dialogue with a significant language component
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : 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.
Type de document :
Communication dans un congrès
3rd International Workshop on Computational Terminology - CompuTerm 2004, 2004, Geneva, Suisse. pp.91-94, 2004
Liste complète des métadonnées
https://hal.inria.fr/inria-00107805
Contributeur : Laurent Romary <>
Soumis le : mardi 14 juillet 2009 - 14:56:49
Dernière modification le : jeudi 5 avril 2018 - 10:36:48
Document(s) archivé(s) le : mardi 6 avril 2010 - 20:11:04

Fichier

W04-1814.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00107805, version 1

Collections

INRIA | UNIV-NANTES | LINA-TALN | LINA | LORIA | UNIV-LORRAINE

Citation

Koichi Takeuchi, Kyo Kageura, Teruo Koyama, Béatrice Daille, Laurent Romary. Construction of Grammar Based Term Extraction Model for Japanese. 3rd International Workshop on Computational Terminology - CompuTerm 2004, 2004, Geneva, Suisse. pp.91-94, 2004. 〈inria-00107805〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

501

Téléchargements de fichiers

189

Contact


archive-ouverte@inria.fr