1 |
Neural machine translation between similar south-Slavic languages
|
|
|
|
In: Popović, Maja orcid:0000-0001-8234-8745 and Poncelas, Alberto orcid:0000-0002-5089-1687 (2020) Neural machine translation between similar south-Slavic languages. In: 2020 Fifth Conference on Machine Translation (WMT20), 19-20 Nov 2020, Dominican Republic (Online). (2020)
|
|
BASE
|
|
Show details
|
|
2 |
Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation
|
|
|
|
In: Soto, Xabier orcid:0000-0002-3622-6496 , Shterionov, Dimitar orcid:0000-0001-6300-797X , Poncelas, Alberto orcid:0000-0002-5089-1687 and Way, Andy orcid:0000-0001-5736-5930 (2020) Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation. In: Annual Conference of the Association for Computational Linguistics, ACL, 5-10 July 2020, Seattle, WA, USA (Online). (2020)
|
|
BASE
|
|
Show details
|
|
3 |
Rapid development of competitive translation engines for access to multilingual COVID-19 information
|
|
|
|
In: Way, Andy orcid:0000-0001-5736-5930 , Haque, Rejwanul orcid:0000-0003-1680-0099 , Xie, Guodong, Gaspari, Federico orcid:0000-0003-3808-8418 , Popović, Maja orcid:0000-0001-8234-8745 and Poncelas, Alberto orcid:0000-0002-5089-1687 (2020) Rapid development of competitive translation engines for access to multilingual COVID-19 information. Informatics . ISSN 2227-9709 (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Using multiple subwords to improve English-Esperanto automated literary translation quality
|
|
|
|
In: Poncelas, Alberto orcid:0000-0002-5089-1687 , Buts, Jan orcid:0000-0002-7657-804X , Hadley, James orcid:0000-0003-1950-2679 and Way, Andy orcid:0000-0001-5736-5930 (2020) Using multiple subwords to improve English-Esperanto automated literary translation quality. In: Workshop on Technologies for MT of Low Resource Languages (AACL-IJCNLP), 4 Dec 2020, Suzhou, China(Online). (2020)
|
|
BASE
|
|
Show details
|
|
5 |
The impact of indirect machine translation on sentiment classification
|
|
|
|
In: Poncelas, Alberto orcid:0000-0002-5089-1687 , Lohar, Pintu, Way, Andy orcid:0000-0001-5736-5930 and Hadley, James orcid:0000-0003-1950-2679 (2020) The impact of indirect machine translation on sentiment classification. In: 14th biennial conference of the Association for Machine Translation in the Americas, AMTA, 6-10 Oct 2020, Orlando, Fl, USA (Virtual). (In Press) (2020)
|
|
BASE
|
|
Show details
|
|
6 |
Facilitating Access to Multilingual COVID-19 Information via Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Adapting NMT to caption translation in Wikimedia Commons for low-resource languages
|
|
|
|
In: Poncelas, Alberto orcid:0000-0002-5089-1687 , Sarasola, Kepa orcid:0000-0003-4349-6088 , Dowling, Meghan orcid:0000-0003-1637-4923 , Way, Andy orcid:0000-0001-5736-5930 , Labaka, Gorka orcid:0000-0003-4611-2502 and Alegria, Iñaki orcid:0000-0002-0272-1472 (2019) Adapting NMT to caption translation in Wikimedia Commons for low-resource languages. Procesamiento de Lenguaje Natural, 63 . pp. 33-40. ISSN 1135-5948 (2019)
|
|
BASE
|
|
Show details
|
|
9 |
Adapting NMT to caption translation in Wikimedia Commons for low-resource languages
|
|
|
|
In: Poncelas, Alberto orcid:0000-0002-5089-1687 , Sarasola, Kepa orcid:0000-0003-4349-6088 , Dowling, Meghan orcid:0000-0003-1637-4923 , Way, Andy orcid:0000-0001-5736-5930 , Labaka, Gorka orcid:0000-0003-4611-2502 and Alegria, Iñaki orcid:0000-0002-0272-1472 (2019) Adapting NMT to caption translation in Wikimedia Commons for low-resource languages. Procesamiento del Lenguaje Natural, 63 . pp. 33-40. ISSN 1135-5948 (2019)
|
|
BASE
|
|
Show details
|
|
10 |
Selecting artificially-generated sentences for fine-tuning neural machine translation
|
|
|
|
In: Poncelas, Alberto orcid:0000-0002-5089-1687 and Way, Andy orcid:0000-0001-5736-5930 (2019) Selecting artificially-generated sentences for fine-tuning neural machine translation. In: 12th International Conference on Natural Language Generation, 29 Oct - 1 Nov 2019, Tokyo, Japan. (2019)
|
|
BASE
|
|
Show details
|
|
11 |
Improving transductive data selection algorithms for machine translation
|
|
Poncelas, Alberto. - : Dublin City University. School of Computing, 2019. : Dublin City University. ADAPT, 2019
|
|
In: Poncelas, Alberto orcid:0000-0002-5089-1687 (2019) Improving transductive data selection algorithms for machine translation. PhD thesis, Dublin City University. (2019)
|
|
BASE
|
|
Show details
|
|
12 |
Combining SMT and NMT back-translated data for efficient NMT
|
|
|
|
In: 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. (2019)
|
|
BASE
|
|
Show details
|
|
13 |
Transductive data-selection algorithms for fine-tuning neural machine translation
|
|
|
|
In: Poncelas, Alberto orcid:0000-0002-5089-1687 , Maillette de Buy Wenniger, Gideon orcid:0000-0001-8427-7055 and Way, Andy orcid:0000-0001-5736-5930 (2019) Transductive data-selection algorithms for fine-tuning neural machine translation. In: The 8th Workshop on Patent and Scientific Literature Translation, Dublin, Ireland. (2019)
|
|
BASE
|
|
Show details
|
|
14 |
Adaptation of machine translation models with back-translated data using transductive data selection methods
|
|
|
|
In: Poncelas, Alberto orcid:0000-0002-5089-1687 , Maillette de Buy Wenniger, Gideon orcid:0000-0001-8427-7055 and Way, Andy orcid:0000-0001-5736-5930 (2019) Adaptation of machine translation models with back-translated data using transductive data selection methods. In: A Proceedings of CICLing 2019, the 20th International Conference on Computational Linguistics and Intelligent Text Processing, 7 - 13 Apr 2019, La Rochelle, France. (2019)
|
|
BASE
|
|
Show details
|
|
15 |
ABI Neural Ensemble Model for Gender Prediction Adapt Bar-Ilan Submission for the CLIN29 Shared Task on Gender Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Adapting NMT to caption translation in Wikimedia Commons for low-resource languages ; Adaptando NMT a la traducción de pies de imagen en Wikimedia Commons para idiomas con pocos recursos
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Extracting in-domain training corpora for neural machine translation using data selection methods
|
|
|
|
In: 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. (2018)
|
|
BASE
|
|
Show details
|
|
18 |
Understanding Meanings in Multilingual Customer Feedback ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Applying N-gram alignment entropy to improve feature decay algorithms
|
|
|
|
In: 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 (2017)
|
|
BASE
|
|
Show details
|
|
20 |
Applying N-gram Alignment Entropy to Improve Feature Decay Algorithms
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 245-256 (2017) (2017)
|
|
Abstract:
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. However, intuitively, more ambiguous n-grams require more training examples in order to adequately estimate their translation probabilities. This ambiguity can be measured by alignment entropy. In this paper we propose two methods for calculating the alignment entropies for n-grams of any size, which can be used for improving the performance of FDA. We evaluate the substitution of the n-gram-specific entropy values computed by these methods to the parameters of both the exponential and linear decay factor of FDA. The experiments conducted on German-to-English and Czech-to-English translation demonstrate that the use of alignment entropies can lead to an increase in the quality of the results of FDA.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doaj.org/article/843f90e9c52844f6836fae65c201ef35 https://doi.org/10.1515/pralin-2017-0024
|
|
BASE
|
|
Hide details
|
|
|
|