Neural Machine Translation by Generating Multiple Linguistic Factors

Abstract : Factored neural machine translation (FNMT) is founded on the idea of using the morphological and grammatical decomposition of the words (factors) at the output side of the neural network. This architecture addresses two well-known problems occurring in MT, namely the size of target language vocabulary and the number of unknown tokens produced in the translation. FNMT system is designed to manage larger vocabulary and reduce the training time (for systems with equivalent target language vocabulary size). Moreover, we can produce grammatically correct words that are not part of the vocabulary. FNMT model is evaluated on IWSLT'15 English to French task and compared to the baseline word-based and BPE-based NMT systems. Promising qualitative and quantitative results (in terms of BLEU and METEOR) are reported.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

Littérature citée [27 références]  Voir  Masquer  Télécharger
Contributeur : Mercedes Garcia-Martinez <>
Soumis le : dimanche 21 janvier 2018 - 18:44:22
Dernière modification le : vendredi 26 avril 2019 - 13:54:02
Archivage à long terme le : jeudi 24 mai 2018 - 06:45:38


Fichiers produits par l'(les) auteur(s)




Mercedes Garcia-Martinez, Loïc Barrault, Fethi Bougares. Neural Machine Translation by Generating Multiple Linguistic Factors. 5th International Conference Statistical Language and Speech Processing SLSP 2017, Oct 2017, Le Mans, France. ⟨10.1007/978-3-319-68456-7_2⟩. ⟨hal-01689270⟩



Consultations de la notice


Téléchargements de fichiers