Compositionality and lexical alignment of multi-word terms - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Language Resources and Evaluation Année : 2010

Compositionality and lexical alignment of multi-word terms

Résumé

The automatic compilation of bilingual lists of terms from specialized comparable corpora using lexical alignment has been successful for single-word terms (SWTs), but remains disappointing for multi-word terms (MWTs). The low frequency and the variability of the syntactic structures of MWTs in the source and the target languages are the main reported problems. This paper defines a general framework dedicated to the lexical alignment of MWTs from comparable corpora that includes a compositional translation process and the standard lexical context analysis. The compositional method which is based on the translation of lexical items being restrictive, we introduce an extended compositional method that bridges the gap between MWTs of different syntactic structures through morphological links. We experimented with the two compositional methods for the French–Japanese alignment task. The results show a significant improvement for the translation of MWTs and advocate further morphological analysis in lexical alignment.

Dates et versions

hal-00417686 , version 1 (16-09-2009)

Identifiants

Citer

Emmanuel Morin, Béatrice Daille. Compositionality and lexical alignment of multi-word terms. Language Resources and Evaluation, 2010, 44 (1/2), pp.79-95. ⟨10.1007/s10579-009-9098-8⟩. ⟨hal-00417686⟩
66 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More