Two-Step MT: Predicting Target Morphology - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Two-Step MT: Predicting Target Morphology

Résumé

This paper describes a two-step machine translation system that addresses the issue of translating into a morphologically rich language (English to Czech), by performing separately the translation and the generation of target morphology. The first step consists in translating from English into a normalized version of Czech, where some morphological information has been removed. The second step retrieves this information and re-inflects the normalized output, turning it into fully inflected Czech. We introduce different setups for the second step and evaluate the quality of their predictions over different MT systems trained on different amounts of parallel and monolingual data and report ways to adapt to different data sizes, which improves the translation in low-resource conditions, as well as when large training data is available.
Fichier principal
Vignette du fichier
Burlot16reinflection.pdf (208.97 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01592337 , version 1 (29-09-2017)

Identifiants

  • HAL Id : hal-01592337 , version 1

Citer

Franck Burlot, Elena Knyazeva, Thomas Lavergne, François Yvon. Two-Step MT: Predicting Target Morphology. International Workshop on Spoken Language Translation, 2016, Seattle, WA, United States. ⟨hal-01592337⟩
109 Consultations
52 Téléchargements

Partager

Gmail Facebook X LinkedIn More