LIMSI@WMT'17 - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

LIMSI@WMT'17

Résumé

This paper describes LIMSI's submissions to the news shared task at WMT'17 for English into Czech and Latvian, as well as related experiments. This year's novelties consist in the use of a neural machine translation system with a factored output predicting simultaneously a lemma decorated with morphological information and a fine-grained part-of-speech. Such a type of system drew our attention to the specific step of reinflection, where lemmas and parts-of-speech are transformed into fully inflected words. Finally, we ran experiments showing an efficient strategy for parameter initialization, as well as data filtering procedures.
Fichier principal
Vignette du fichier
W17-4721.pdf (200.18 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01619897 , version 1 (19-10-2017)

Identifiants

  • HAL Id : hal-01619897 , version 1

Citer

Franck Burlot, Pooyan Safari, Matthieu Labeau, Alexandre Allauzen, François Yvon. LIMSI@WMT'17. Conference on Machine Translation, Association for Computational Linguistics, Jan 2017, Copenhagen, Denmark. pp.257 - 264. ⟨hal-01619897⟩
100 Consultations
160 Téléchargements

Partager

Gmail Facebook X LinkedIn More