Using Monolingual Data in Neural Machine Translation: a Systematic Study

Autor: Franck Burlot, François Yvon

Publikováno v: Proceedings of the Third Conference on Machine Translation: Research Papers
Conference on Machine Translation
Conference on Machine Translation, Oct 2018, Brussels, Belgium
WMT

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: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::334d5ba91b0b41b7d3e84b7e7ed07746

LIMSI$@$WMT'17

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

Publikováno v: WMT

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 pred

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5524e27a4f1738ecdfe60057ab4505db
https://doi.org/10.18653/v1/w17-4721

Learning Morphological Normalization for Translation from and into Morphologically Rich Languages

Autor: François Yvon, Franck Burlot

Publikováno v: The Prague Bulletin of Mathematical Linguistics
The Prague Bulletin of Mathematical Linguistics, Univerzita Karlova v Praze, 2017, 108, pp.49-60. ⟨10.1515/pralin-2017-0008⟩
The Prague Bulletin of Mathematical Linguistics, 2017, 108, pp.49-60. ⟨10.1515/pralin-2017-0008⟩
Prague Bulletin of Mathematical Linguistics, Vol 108, Iss 1, Pp 49-60 (2017)

When translating between a morphologically rich language (MRL) and English, word forms in the MRL often encode grammatical information that is irrelevant with respect to English, leading to data sparsity issues. This problem can be mitigated by remov

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8daf0f6eb1d09021017c73c94ad49f78
https://hal.archives-ouvertes.fr/hal-01618382

The QT21/HimL Combined Machine Translation System

Autor: Matthias Huck, Alexander Fraser, Thomas Lavergne, Stella Frank, Fabienne Braune, Marcis Pinnis, Barry Haddow, Tamer Alkhouli, Ondrej Bojar, Rico Sennrich, Frédéric Blain, Jan-Thorsten Peter, Hermann Ney, Alexandre Allauzen, Franck Burlot, Lucia Specia, Jan Niehues, Alex Waibel, Lauriane Aufrant, Aleš Tamchyna, Elena Knyazeva, François Yvon

Publikováno v: Stroudsburg, PA : Association for Computational Linguistics 344-355 (2016). doi:10.18653/v1/W16-2320
The 54th Annual Meeting of the Association for Computational Linguistics-proceedings of the First Conference on Machine Translation (WMT) : August 7-12, 2016, Berlin, Germany : ACL 2016.-Volume 2, Shared Task Papers
The 54th Annual Meeting of the Association for Computational Linguistics-proceedings of the First Conference on Machine Translation (WMT) : August 7-12, 2016, Berlin, Germany : ACL 2016.-Volume 2, Shared Task Papers1. Conference on Machine Translation, WMT16, Berlin, Germany, 2016-08-11-2016-08-12
WMT
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers
Peter, J-T, Alkhouli, T, Ney, H, Huck, M, Braune, F, Fraser, A, Tamchyna, A, Bojar, O, Haddow, B, Sennrich, R, Blain, F, Specia, L, Niehues, J, Waibel, A, Allauzen, A, Aufrant, L, Burlot, F, knyazeva, E, Lavergne, T, Yvon, F, Frank, S & Pinnis, M 2016, The QT21/HimL Combined Machine Translation System . in Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers . Berlin, Germany, pp. 344–355, First Conference on Machine Translation, Berlin, Germany, 11/08/16 . https://doi.org/10.18653/v1/W16-2320
First Conference on Machine Translation (WMT16) Proceedings
First Conference on Machine Translation (WMT16)
First Conference on Machine Translation (WMT16), Aug 2016, Berlin, Germany. pp.344-355, ⟨10.18653/v1/W16-2320⟩

International audience; This paper describes the joint submission of the QT21 and HimL projects for the English→Romanian translation task of the ACL 2016 First Conference on Machine Translation (WMT 2016). The submission is a system combination whi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7dd24de867e6a53c710f0bfd7c2e855

LIMSI$@$WMT’16: Machine Translation of News

Autor: Guillaume Wisniewski, Franck Burlot, Thomas Lavergne, Lauriane Aufrant, Elena Knyazeva, François Yvon, Alexandre Allauzen, Ophélie Lacroix

Publikováno v: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers
First Conference on Machine Translation
First Conference on Machine Translation, Aug 2016, Berlin, Germany. pp.239--245, ⟨10.18653/v1/W16-2304⟩
Stroudsburg, PA : Association for Computational Linguistics 239-245 (2016). doi:10.18653/v1/W16-2304
The 54th Annual Meeting of the Association for Computational Linguistics-proceedings of the First Conference on Machine Translation (WMT) : August 7-12, 2016, Berlin, Germany : ACL 2016.-Volume 2, Shared Task Papers
The 54th Annual Meeting of the Association for Computational Linguistics-proceedings of the First Conference on Machine Translation (WMT) : August 7-12, 2016, Berlin, Germany : ACL 2016.-Volume 2, Shared Task Papers1. Conference on Machine Translation, Berlin, Germany, 2016-08-11-2016-08-12
WMT

International audience; This paper describes LIMSI’s submissions to the shared WMT’16 task “Translation of News”. We report results for Romanian-English in both directions, for English to Russian, as well as preliminary experiments on reorder

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5aac94ec64bc40b6e9c9fdd209485bd5