Learning Morphological Normalization for Translation from and into Morphologically Rich Languages - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue The Prague Bulletin of Mathematical Linguistics Année : 2017

Learning Morphological Normalization for Translation from and into Morphologically Rich Languages

Résumé

When translating between a morphologically rich language (MRL) and English, word forms in the MRL often encode grammatical information that is irrelevant with respect to English, leading to data sparsity issues. This problem can be mitigated by removing from the MRL irrelevant information through normalization. Such preprocessing is usually performed in a deterministic fashion, using hand-crafted rules and yielding suboptimal representations. We introduce here a simple way to automatically compute an appropriate normalization of the MRL and show that it can improve machine translation in both directions.
Fichier principal
Vignette du fichier
art-burlot-yvon.pdf (203.69 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01618382 , version 1 (17-10-2017)

Identifiants

Citer

Franck Burlot, François Yvon. Learning Morphological Normalization for Translation from and into Morphologically Rich Languages. The Prague Bulletin of Mathematical Linguistics, 2017, 108, pp.49-60. ⟨10.1515/pralin-2017-0008⟩. ⟨hal-01618382⟩
123 Consultations
142 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More