Neural Machine Translation by Generating Multiple Linguistic Factors

Mercedes Garcia-Martinez 1 Loïc Barrault 1 Fethi Bougares 1
1 LIUM - Laboratoire d'Informatique de l'Université du Mans
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.
Keywords : Neural Networks Deep Learning Machine Translation Factored representation
Type de document :
Communication dans un congrès
Liste complète des métadonnées

Littérature citée [27 références]  Voir  Masquer  Télécharger
https://hal-univ-lemans.archives-ouvertes.fr/hal-01689270
Contributeur : Mercedes Garcia-Martinez <>
Soumis le : dimanche 21 janvier 2018 - 18:44:22
Dernière modification le : vendredi 26 avril 2019 - 13:54:02
Document(s) archivé(s) le : jeudi 24 mai 2018 - 06:45:38

Fichier

SLSP17.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

UNIV-LEMANS | LIUM | LIUM-LST

Citation

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⟩

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

253

Téléchargements de fichiers

161

Contact

CCSD