Rapid Development of Competitive Translation Engines for Access to Multilingual COVID-19 Information

Autor: Andy Way, Rejwanul Haque, Guodong Xie, Federico Gaspari, Maja Popović, Alberto Poncelas

Publikováno v: Informatics, Vol 7, Iss 2, p 19 (2020)

Every day, more people are becoming infected and dying from exposure to COVID-19. Some countries in Europe like Spain, France, the UK and Italy have suffered particularly badly from the virus. Others such as Germany appear to have coped extremely wel

Externí odkaz: https://doaj.org/article/0b5e0b6b2e174698844011aa12919538

Applying N-gram Alignment Entropy to Improve Feature Decay Algorithms

Autor: Alberto Poncelas, Andy Way, Gideon Maillette de Buy Wenniger

Publikováno v: Prague Bulletin of Mathematical Linguistics, Vol 108, Iss 1, Pp 245-256 (2017)
The Prague Bulletin of Mathematical Linguistics
Poncelas, Alberto ORCID: 0000-0002-5089-1687 , Maillette de Buy Wenniger, Gideon and Way, Andy ORCID: 0000-0001-5736-5930 (2017) Applying N-gram alignment entropy to improve feature decay algorithms. The Prague Bulletin of Mathematical Linguistics (108). pp. 245-256. ISSN 0032-6585

Data Selection is a popular step in Machine Translation pipelines. Feature Decay Algorithms (FDA) is a technique for data selection that has shown a good performance in several tasks. FDA aims to maximize the coverage of n-grams in the test set. Howe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::63b421cf2c3c72453905ab8d35d6d518
https://doaj.org/article/843f90e9c52844f6836fae65c201ef35

Combining SMT and NMT back-translated data for efficient NMT

Autor: Gideon Maillette de Buy Wenniger, Andy Way, Dimitar Shterionov, Maja Popović, Alberto Poncelas

Publikováno v: Poncelas, Alberto ORCID: 0000-0002-5089-1687 , Popović, Maja ORCID: 0000-0001-8234-8745 , Shterionov, Dimitar ORCID: 0000-0001-6300-797X , Maillette de Buy Wenniger, Gideon and Way, Andy ORCID: 0000-0001-5736-5930 (2019) Combining SMT and NMT back-translated data for efficient NMT. In: Recent Advances in Natural Language Processing (RANLP 2019), 2-4 Sept 2019, Varna, Bulgaria.
Scopus-Elsevier
Tilburg University-PURE
RANLP

Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. One of these methods is back-transla

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4969e950485870897dfabc3ba1475bcb
http://doras.dcu.ie/24272/

Extracting in-domain training corpora for neural machine translation using data selection methods

Autor: Catarina Cruz Silva, Andy Way, Alberto Poncelas, Chao-Hong Liu

Publikováno v: Cruz Silva, Catarina, Liu, Chao-Hong ORCID: 0000-0002-1235-6026 , Poncelas, Alberto ORCID: 0000-0002-5089-1687 and Way, Andy ORCID: 0000-0001-5736-5930 (2018) Extracting in-domain training corpora for neural machine translation using data selection methods. In: Third Conference on Machine Translation (WMT), 31 Oct-1 Nov 2018, Belgium, Brussels.
WMT

Data selection is a process used in selecting a subset of parallel data for the training of machine translation (MT) systems, so that 1) resources for training might be reduced, 2) trained models could perform better than those trained with the whole

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::398a2b747a6d059ab7ded099a78abb47
http://doras.dcu.ie/23338/

Investigating Backtranslation in Neural Machine Translation

Autor: Alberto Poncelas, Dimitar Shterionov, Andy Way, Gideon Maillette De Buy Wenniger, Peyman Passban

Publikováno v: RUA. Repositorio Institucional de la Universidad de Alicante
Universidad de Alicante (UA)
Scopus-Elsevier
Poncelas, Alberto ORCID: 0000-0002-5089-1687 , Shterionov, Dimitar ORCID: 0000-0001-6300-797X , Way, Andy ORCID: 0000-0001-5736-5930 , Maillette de Buy Wenniger, Gideon and Passban, Peyman (2018) Investigating backtranslation in neural machine translation. In: 21st Annual Conference of The European Association for Machine Translation, 28-30 May 2018, Alicante, Spain.
Poncelas, Alberto ORCID: 0000-0002-5089-1687 , Shterionov, Dimitar ORCID: 0000-0001-6300-797X , Way, Andy ORCID: 0000-0001-5736-5930 , Maillette de Buy Wenniger, Gideon and Passban, Peyman (2018) Investigating backtranslation in neural machine translation. In: 21st Annual Conference
Tilburg University-PURE

A prerequisite for training corpus-based machine translation (MT) systems – either Statistical MT (SMT) or Neural MT (NMT) – is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT has bee

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::694f2196d4c1b5f9e93f7ebf1b26b611
https://hdl.handle.net/10045/76085