Skip to Main content Skip to Navigation
Conference papers

Word Representations in Factored Neural Machine Translation

Abstract : Translation into a morphologically rich language requires a large output vocabulary to model various morphological phenomena, which is a challenge for neural machine translation architectures. To address this issue, the present paper investigates the impact of having two output factors with a system able to generate separately two distinct representations of the target words. Within this framework, we investigate several word representations that correspond to different distributions of morpho-syntactic information across both factors. We report experiments for translation from English into two morphologically rich languages, Czech and Latvian, and show the importance of explicitly modeling target morphology.
Complete list of metadata

Cited literature [30 references]  Display  Hide  Download
Contributor : Dev.Limsi Dev.Limsi <>
Submitted on : Tuesday, February 13, 2018 - 10:11:15 AM
Last modification on : Thursday, December 10, 2020 - 12:32:05 PM
Long-term archiving on: : Monday, May 14, 2018 - 12:33:32 PM


Publisher files allowed on an open archive


  • HAL Id : hal-01618384, version 1


Franck Burlot, Mercedes Garcia-Martinez, Loïc Barrault, Fethi Bougares, François Yvon. Word Representations in Factored Neural Machine Translation. Conference on Machine Translation, Association for Computational Linguistics, Sep 2017, Copenhagen, Denmark. pp.43 - 55. ⟨hal-01618384⟩



Record views


Files downloads