Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Fethi Bougares"'
Publikováno v:
Machine Translation. 34:1-20
Translating between morphologically rich languages is still challenging for current machine translation systems. In this paper, we experiment with various neural machine translation (NMT) architectures to address the data sparsity problem caused by d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c14fdedc994e751afc64b10efb40f7be
https://doi.org/10.1007/s10590-019-09242-9
https://doi.org/10.1007/s10590-019-09242-9
Autor:
Le, Hang, Barbier, Florentin, Nguyen, Ha, Tomashenko, Natalia, Mdhaffar, Salima, Gahbiche, Souhir, Fethi, Bougares, Lecouteux, Benjamin, Schwab, Didier, Estève, Yannick
Publikováno v:
Proceedings of the 18th International Conference on Spoken Language Translation
International Conference on Spoken Language Translation (IWSLT)
International Conference on Spoken Language Translation (IWSLT), Aug 2021, Bangkok (virtual), Thailand. ⟨10.18653/v1/2021.iwslt-1.20⟩
IWSLT
International Conference on Spoken Language Translation (IWSLT)
International Conference on Spoken Language Translation (IWSLT), Aug 2021, Bangkok (virtual), Thailand. ⟨10.18653/v1/2021.iwslt-1.20⟩
IWSLT
International audience; This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2021, low-resource speech translation and multilingual speech translation. The ON-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b29da0e4c2de43ba533c62e641a319f
https://hal.archives-ouvertes.fr/hal-03298854v2/file/v2--ON_TRAC_IWSLT21.pdf
https://hal.archives-ouvertes.fr/hal-03298854v2/file/v2--ON_TRAC_IWSLT21.pdf
Publikováno v:
Interspeech 2020
Interspeech 2020, Oct 2020, Shangai (Virtual Conf), China
INTERSPEECH
Interspeech 2020, Oct 2020, Shangai (Virtual Conf), China
INTERSPEECH
International audience; Self-supervised learning from raw speech has been proven beneficial to improve automatic speech recognition (ASR). We investigate here its impact on end-to-end automatic speech translation (AST) performance. We use a contrasti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::139a6b14594988921a9cd8230c576616
https://hal.archives-ouvertes.fr/hal-02962186/file/Paper_Template_for_INTERSPEECH_2019-3.pdf
https://hal.archives-ouvertes.fr/hal-02962186/file/Paper_Template_for_INTERSPEECH_2019-3.pdf
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783030493417
ISDA
ISDA
Plagiarism is the process of using the ideas of another without naming the source. Plagiarism is unacceptable and could be viewed as cheating and stealing. Plagiarism detection is necessary but complicated as it is often facing significant challenges
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc1adcdd4fb8a6556b59e38bbc74e947
https://doi.org/10.1007/978-3-030-49342-4_21
https://doi.org/10.1007/978-3-030-49342-4_21
Autor:
Antoine Caubrière, Natalia A. Tomashenko, Fethi Bougares, Laurent Besacier, Yannick Estève, Benjamin Lecouteux, Ha Nguyen, Maha Elbayad
Publikováno v:
Proceedings of the 17th International Conference on Spoken Language Translation
Proceedings of the 17th International Conference on Spoken Language Translation, Jul 2020, Seattle, WA, United States. pp.35-43, ⟨10.18653/v1/2020.iwslt-1.2⟩
IWSLT
Proceedings of the 17th International Conference on Spoken Language Translation, Jul 2020, Seattle, WA, United States. pp.35-43, ⟨10.18653/v1/2020.iwslt-1.2⟩
IWSLT
International audience; This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2020, offline speech translation and simultaneous speech translation. ON-TRAC Cons
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::44193eda587bbb73c4a9986ce31b819c
http://arxiv.org/abs/2005.11861
http://arxiv.org/abs/2005.11861
Autor:
Adrien Bardet, Mercedes García-Martínez, Fethi Bougares, Ozan Caglayan, Walid Aransa, Loïc Barrault
Publikováno v:
Prague Bulletin of Mathematical Linguistics, Vol 109, Iss 1, Pp 15-28 (2017)
The Prague Bulletin of Mathematical Linguistics
The Prague Bulletin of Mathematical Linguistics, Univerzita Karlova v Praze, 2017, 109 (1), ⟨10.1515/pralin-2017-0035⟩
The Prague Bulletin of Mathematical Linguistics
The Prague Bulletin of Mathematical Linguistics, Univerzita Karlova v Praze, 2017, 109 (1), ⟨10.1515/pralin-2017-0035⟩
In this paper, we present nmtpy, a flexible Python toolkit based on Theano for training Neural Machine Translation and other neural sequence-to-sequence architectures. nmtpy decouples the specification of a network from the training and inference uti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6de5ee9a35875d12a214514a998ffa0
https://doaj.org/article/718b4d8987474adfb74e46eaa976551b
https://doaj.org/article/718b4d8987474adfb74e46eaa976551b
Publikováno v:
BASE-Bielefeld Academic Search Engine
Language Resources and Evaluation
Language Resources and Evaluation, Springer Verlag, 2018, 52 (1), pp.249-267. ⟨10.1007/s10579-017-9402-y⟩
Language Resources and Evaluation
Language Resources and Evaluation, Springer Verlag, 2018, 52 (1), pp.249-267. ⟨10.1007/s10579-017-9402-y⟩
International audience; Although Modern Standard Arabic is taught in schools and used in written communication and TV/radio broadcasts, all informal communication is typically carried out in dialectal Arabic. In this work, we focus on the design of s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2b0b6824871a872b0ab784c3a57f88e
https://doi.org/10.1007/s10579-017-9402-y
https://doi.org/10.1007/s10579-017-9402-y
Publikováno v:
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), Aug 2019, Florence, France. pp.129-133, ⟨10.18653/v1/W19-5307⟩
WMT (2)
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), Aug 2019, Florence, France. pp.129-133, ⟨10.18653/v1/W19-5307⟩
WMT (2)
This paper describes the neural machine translation (NMT) systems of the LIUM Laboratory developed for the French↔German news translation task of the Fourth Conference onMachine Translation (WMT 2019). The chosen language pair is included for the f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::88e5952247a55a5841ca93313ecd7882
https://hal.archives-ouvertes.fr/hal-02405788
https://hal.archives-ouvertes.fr/hal-02405788
Publikováno v:
Statistical Language and Speech Processing ISBN: 9783030313715
SLSP
SLSP
Transfer learning is an interesting approach to tackle the low resource languages machine translation problem. Transfer learning, as a machine learning algorithm, requires to make several choices such as selecting the training data and more particula
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb8f21f43420dcf5df8f621945b9443f
https://doi.org/10.1007/978-3-030-31372-2_5
https://doi.org/10.1007/978-3-030-31372-2_5
Publikováno v:
TALN 2019
TALN 2019, Jul 2019, Toulouse, France
TALN 2019, Jul 2019, Toulouse, France
National audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::06084e56cb86063ad6a77fd74d59ac92
https://hal.archives-ouvertes.fr/hal-02436510
https://hal.archives-ouvertes.fr/hal-02436510