Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Antonio Valerio Miceli Barone"'
Publikováno v:
Computational Linguistics, Vol 48, Iss 3 (2022)
We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the world and almost all language pairs lack significant resources for training machine translat
Externí odkaz:
https://doaj.org/article/c67ef92aeb924e50a96fada3b039dfa7
Publikováno v:
Valerio Miceli Barone, A, Birch, A & Sennrich, R 2022, Distributionally Robust Recurrent Decoders with Random Network Distillation . in S Gella, H He, B P Majumdar, B Can, E Giunchiglia, S Cahyawijaya, S Min, M Mozes, X L Li, I Augenstein, A Rogers, K Cho, E Grefenstette, L Rimell & C Dyer (eds), Proceedings of the 7th Workshop on Representation Learning for NLP . Dublin, Ireland, pp. 1-8, The 7th Workshop on Representation Learning for NLP, Dublin, Ireland, 26/05/22 . https://doi.org/10.18653/v1/2022.repl4nlp-1.1
Neural machine learning models can successfully model language that is similar to their training distribution, but they are highly susceptible to degradation under distribution shift, which occurs in many practical applications when processing out-of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb5e045de2fd5664d8981c1e885f21ee
https://doi.org/10.5167/uzh-224512
https://doi.org/10.5167/uzh-224512
Autor:
Alexandra Birch, Barry Haddow, Antonio Valerio Miceli Barone, Jindrich Helcl, Jonas Waldendorf, Felipe Sánchez Martínez, Mikel Forcada, Víctor Sánchez Cartagena, Juan Antonio Pérez-Ortiz, Miquel Esplà-Gomis, Wilker Aziz, Lina Murady, Sevi Sariisik, Peggy van der Kreeft, Kay Macquarrie
Publikováno v:
ZENODO
In the media industry and the focus of global reporting can shift overnight. There is a compelling need to be able to develop new machine translation systems in a short period of time and in order to more efficiently cover quickly developing stories.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6a1f77f54eb25cbb9c9310eae74c0c7b
https://doi.org/10.5281/zenodo.6580252
https://doi.org/10.5281/zenodo.6580252
Autor:
Sheila Castilho, Joss Moorkens, Gaspari F, Rico Sennrich, Vilelmini Sosoni, Panayota Georgakopoulou, Pintu Lohar, Andy Way, Antonio Valerio Miceli Barone, Maria Gialama
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3730::aad0ea36a14065369bd7b7b1bbc8cc40
http://hdl.handle.net/11588/894224
http://hdl.handle.net/11588/894224
Autor:
Roman Grundkiewicz, Denis Emelin, Antonio Valerio Miceli Barone, Rico Sennrich, Ulrich Germann, Barry Haddow, Nikolay Bogoychev, Kenneth Heafield
Publikováno v:
WMT (shared task)
The University of Edinburgh made submissions to all 14 language pairs in the news translation task, with strong performances in most pairs. We introduce new RNN-variant, mixed RNN/Transformer ensembles, data selection and weighting, and extensions to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a4127f9be1ba25eef2ab64abf8e7ab52
https://doi.org/10.18653/v1/w18-6412
https://doi.org/10.18653/v1/w18-6412
Publikováno v:
Currey, A, Miceli Barone, A & Heafield, K 2017, Copied Monolingual Data Improves Low-Resource Neural Machine Translation . in Proceedings of the Second Conference on Machine Translation : Part of EMNLP 2017 . vol. 1: Research Papers, pp. 148–156, 2017 Conference on Machine Translation, Copenhagen, Denmark, 7/09/17 . https://doi.org/10.18653/v1/W17-4715
University of Edinburgh-PURE
WMT
University of Edinburgh-PURE
WMT
We train a neural machine translation (NMT) system to both translate sourcelanguage text and copy target-language text, thereby exploiting monolingual corpora in the target language. Specifically, we create a bitext from the monolingual text in the t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c69c57d76e04a8292eb589b2f702a48
https://hdl.handle.net/20.500.11820/7ed5dde1-7c0d-4522-ba46-f516a6e6c1b8
https://hdl.handle.net/20.500.11820/7ed5dde1-7c0d-4522-ba46-f516a6e6c1b8
Autor:
Antonio Valerio Miceli Barone, Alexandra Birch, Barry Haddow, Ulrich Germann, Kenneth Heafield, Philip Williams, Rico Sennrich, Anna Currey
Publikováno v:
Sennrich, R, Birch, A, Currey, A, Germann, U, Haddow, B, Heafield, K, Miceli Barone, A V & Williams, P 2017, The University of Edinburgh’s Neural MT Systems for WMT17 . in Proceedings of the Second Conference on Machine Translation . pp. 389-399, Second Conference on Machine Translation, Copenhagen, Denmark, 7/09/17 . https://doi.org/10.18653/v1/W17-4739
WMT
Proceedings of the Second Conference on Machine Translation
WMT
Proceedings of the Second Conference on Machine Translation
This paper describes the University of Edinburgh's submissions to the WMT17 shared news translation and biomedical translation tasks. We participated in 12 translation directions for news, translating between English and Czech, German, Latvian, Russi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::05ea5892068beabb57f5e65f8c58a0e0
https://www.pure.ed.ac.uk/ws/files/40220895/wmt17_description_1.pdf
https://www.pure.ed.ac.uk/ws/files/40220895/wmt17_description_1.pdf
Autor:
Alexandra Birch, Marcin Junczys-Dowmunt, Samuel Läubli, Barry Haddow, Kyunghyun Cho, Julian Hitschler, Antonio Valerio Miceli Barone, Maria Nadejde, Rico Sennrich, Jozef Mokry, Orhan Firat
Publikováno v:
Sennrich, R, Firat, O, Cho, K, Birch-Mayne, A, Haddow, B, Hitschler, J, Junczys-Dowmunt, M, Läubli, S, Miceli Barone, A V, Mokry, J & Nadejde, M 2017, Nematus: a Toolkit for Neural Machine Translation . in Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics . Valencia, Spain, pp. 65-68, 15th EACL 2017 Software Demonstrations, Valencia, Spain, 3/04/17 . https://doi.org/10.18653/v1/E17-3017
Sennrich, R, Firat, O, Cho, K, Birch-Mayne, A, Haddow, B, Hitschler, J, Junczys-Dowmunt, M, Läubli, S, Miceli Barone, A, Mokry, J & Nadejde, M 2017, Nematus: a Toolkit for Neural Machine Translation . in Proceedings of the EACL 2017 Software Demonstrations . Association for Computational Linguistics (ACL), pp. 65-68 .
Sennrich, Rico; Firat, Orhan; Cho, Kyunghyun; Birch, Alexandra; Haddow, Barry; Hitschler, Julian; Junczys-Dowmunt, Marcin; Läubli, Samuel; Miceli Barone, Antonio Valerio; Mokry, Jozef; Nadejde, Maria (2017). Nematus: a Toolkit for Neural Machine Translation. In: Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain, 3 April 2017-7 April 2017, 65-68.
Zurich Open Repository and Archive
Edinburgh Research Explorer
arXiv.org e-Print Archive
EACL (Software Demonstrations)
Scopus-Elsevier
Sennrich, R, Firat, O, Cho, K, Birch-Mayne, A, Haddow, B, Hitschler, J, Junczys-Dowmunt, M, Läubli, S, Miceli Barone, A, Mokry, J & Nadejde, M 2017, Nematus: a Toolkit for Neural Machine Translation . in Proceedings of the EACL 2017 Software Demonstrations . Association for Computational Linguistics (ACL), pp. 65-68 .
Sennrich, Rico; Firat, Orhan; Cho, Kyunghyun; Birch, Alexandra; Haddow, Barry; Hitschler, Julian; Junczys-Dowmunt, Marcin; Läubli, Samuel; Miceli Barone, Antonio Valerio; Mokry, Jozef; Nadejde, Maria (2017). Nematus: a Toolkit for Neural Machine Translation. In: Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain, 3 April 2017-7 April 2017, 65-68.
Zurich Open Repository and Archive
Edinburgh Research Explorer
arXiv.org e-Print Archive
EACL (Software Demonstrations)
Scopus-Elsevier
We present Nematus, a toolkit for Neural Machine Translation. The toolkit prioritizes high translation accuracy, usability, and extensibility. Nematus has been used to build top-performing submissions to shared translation tasks at WMT and IWSLT, and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a2e1a64953f6ec2cbeebd30503b1984
https://hdl.handle.net/20.500.11820/115cdfe3-231e-4c87-929e-e55787916b26
https://hdl.handle.net/20.500.11820/115cdfe3-231e-4c87-929e-e55787916b26
Publikováno v:
WMT
Miceli Barone, A V, Helcl, J, Sennrich, R, Haddow, B & Birch, A 2017, Deep Architectures for Neural Machine Translation . in Proceedings of the Second Conference on Machine Translation, Volume 1: Research Papers . Copenhagen, Denmark, pp. 99-107, Second Conference on Machine Translation, Copenhagen, Denmark, 7/09/17 . https://doi.org/10.18653/v1/W17-4710
Proceedings of the Second Conference on Machine Translation
Miceli Barone, A V, Helcl, J, Sennrich, R, Haddow, B & Birch, A 2017, Deep Architectures for Neural Machine Translation . in Proceedings of the Second Conference on Machine Translation, Volume 1: Research Papers . Copenhagen, Denmark, pp. 99-107, Second Conference on Machine Translation, Copenhagen, Denmark, 7/09/17 . https://doi.org/10.18653/v1/W17-4710
Proceedings of the Second Conference on Machine Translation
It has been shown that increasing model depth improves the quality of neural machine translation. However, different architectural variants to increase model depth have been proposed, and so far, there has been no thorough comparative study. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c6097e33e2938a92bd722311e392c4a
https://doi.org/10.18653/v1/w17-4710
https://doi.org/10.18653/v1/w17-4710
Publikováno v:
EMNLP
Miceli Barone, A, Haddow, B, Germann, U & Sennrich, R 2017, Regularization techniques for fine-tuning in neural machine translation . in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing . Copenhagen, Denmark, pp. 1489-1494, EMNLP 2017: Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 7/09/17 . https://doi.org/10.18653/v1/D17-1156
Miceli Barone, A, Haddow, B, Germann, U & Sennrich, R 2017, Regularization techniques for fine-tuning in neural machine translation . in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing . Copenhagen, Denmark, pp. 1489-1494, EMNLP 2017: Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 7/09/17 . https://doi.org/10.18653/v1/D17-1156
We investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset. In this scenario, overfitting is a major challenge. We
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8005a3d31af0484c9325703b7eaed70