A Multi-view Approach for Term Translation Spotting - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

A Multi-view Approach for Term Translation Spotting

Raphaël Rubino
  • Fonction : Auteur
  • PersonId : 776116
  • IdRef : 172390621
Georges Linarès

Résumé

This paper presents a multi-view approach for term translation spotting, based on a bilingual lexicon and comparable corpora. We propose to study different levels of representation for a term: the context , the theme and the orthography. These three approaches are studied individually and combined in order to rank translation candidates. We focus our task on French-English medical terms. Experiments show a significant improvement of the classical context-based approach, with a F-score of 40.3 % for the first ranked translation candidates.

Dates et versions

hal-01320246 , version 1 (23-05-2016)

Identifiants

Citer

Raphaël Rubino, Georges Linarès. A Multi-view Approach for Term Translation Spotting. 12th International Conference, CICLing, Feb 2011, Tokyo, Japan. ⟨10.1007/978-3-642-19437-5_3⟩. ⟨hal-01320246⟩

Collections

UNIV-AVIGNON LIA
27 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More