Using Monolingual Data in Neural Machine Translation: a Systematic Study

Autor: Burlot, Franck, Yvon, François

Neural Machine Translation (MT) has radically changed the way systems are developed. A major difference with the previous generation (Phrase-Based MT) is the way monolingual target data, which often abounds, is used in these two paradigms. While Phra

Externí odkaz: http://arxiv.org/abs/1903.11437

Évaluation morphologique pour la traduction automatique: adaptation au français

Autor: Burlot, Franck, Yvon, François

Publikováno v: Actes de la conférence TALN 2018
Conférence sur le Traitement Automatique des Langues Naturelles
Conférence sur le Traitement Automatique des Langues Naturelles, May 2018, Rennes, France

Le nouvel état de l'art en traduction automatique (TA) s'appuie sur des méthodes neuronales, qui différent profondément des méthodes utilisées antérieurement. Les métriques automatiques classiques sontmal adaptées pour rendre compte de la na

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7bd21e5da3aed9e9828ab1c2a0a3c084
https://hal.archives-ouvertes.fr/hal-01793785/file/morpho-eval.pdf

LIMSI@WMT'17

Autor: Burlot, Franck, Safari, Pooyan, Labeau, Matthieu, Allauzen, Alexandre, Yvon, François

Publikováno v: Proceedings of the Conference on Machine Translation (WMT)
Conference on Machine Translation
Conference on Machine Translation, Association for Computational Linguistics, Jan 2017, Copenhagen, Denmark. pp.257-264

International audience; 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 wit

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______212::f6fe4dc27bbd74db07f0d4574e7fb06b
https://hal.archives-ouvertes.fr/hal-01619897/file/W17-4721.pdf

Two-Step MT: Predicting Target Morphology

Autor: Burlot, Franck, Knyazeva, Elena, Lavergne, Thomas, Yvon, François

Publikováno v: International Workshop on Spoken Language Translation
International Workshop on Spoken Language Translation, 2016, Seattle, WA, United States

International audience; 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

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ef9bf7c40ab147788429a84ae80b034f
https://hal.archives-ouvertes.fr/hal-01592337/file/Burlot16reinflection.pdf

Morphology-Aware Alignments for Translation to and from a Synthetic Language

Autor: Burlot, Franck, Yvon, François

Publikováno v: International Workshop on Spoken Language Translation
International Workshop on Spoken Language Translation, Jan 2015, Da Nang, Vietnam
188-195 (2015).
Proceedings of the International Workshop on Spoken Language Translation : December 3-4, 2015, Da Nang, Vietnam / Edited by Marcello Federico, Sebastian Stüker, Jan Niehues
Proceedings of the International Workshop on Spoken Language Translation : December 3-4, 2015, Da Nang, Vietnam / Edited by Marcello Federico, Sebastian Stüker, Jan NiehuesInternational Workshop on Spoken Language Translation, IWSTL, Da Nang, Vietnam, 2015-12-03-2015-12-04

International audience; Most statistical translation models rely on the unsupervized computation of word-based alignments, which both serve to identify elementary translation units and to uncover hidden translation derivations. It is widely acknowled

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c111618c7ff46c922d30aefd68816b32
https://hal.archives-ouvertes.fr/hal-01635005