Attempting to Bypass Alignment from Comparable Corpora via Pivot Language - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Attempting to Bypass Alignment from Comparable Corpora via Pivot Language

Alexis Linard
  • Fonction : Auteur
  • PersonId : 969266
Emmanuel Morin

Résumé

Alignment from comparable corpora usually involves two languages, one source and one target language. Previous works on bilingual lexicon extraction from parallel corpora demonstrated that more than two languages can be useful to improve the alignments. Our works have investigated to which extent a third language could be interesting to bypass the original alignment. We have defined two original alignment approaches involving pivot languages and we have evaluated over four languages and two pivot languages in particular. The experiments have shown that in some cases the quality of the extracted lexicon has been enhanced.
Fichier non déposé

Dates et versions

hal-01188570 , version 1 (31-08-2015)

Identifiants

  • HAL Id : hal-01188570 , version 1

Citer

Alexis Linard, Béatrice Daille, Emmanuel Morin. Attempting to Bypass Alignment from Comparable Corpora via Pivot Language. 8th Workshop on Building and Using Comparable Corpora (BUCC), Jul 2015, Beijing, China. pp.32-37. ⟨hal-01188570⟩
46 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More