1 |
Investigating query expansion and coreference resolution in question answering on BERT
|
|
|
|
In: Bhattacharjee, Santanu, Haque, Rejwanul orcid:0000-0003-1680-0099 , Maillette de Buy Wenniger, Gideon and Way, Andy orcid:0000-0001-5736-5930 (2020) Investigating query expansion and coreference resolution in question answering on BERT. In: 25th International Conference on Natural Language & Information Systems (NLDB 2020)), 24 - 26 June 2020, Saarbrücken, Germany (Online). ISBN 978-3-030-51309-2 (2020)
|
|
BASE
|
|
Show details
|
|
2 |
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)
|
|
Abstract:
In this work, we study different ways of improving Machine Translation models by using the subset of training data that is the most relevant to the test set. This is achieved by using Transductive Algoritms (TA) for data selection. In particular, we explore two methods: Infrequent N-gram Recovery (INR) and Feature Decay Algorithms (FDA). Statistical Machine Translation (SMT) models do not always perform better when more data are used for training. Using these techniques to extract the training sentences leads to a better performance of the models for translating a particular test set than using the complete training dataset. Neural Machine Translation (NMT) can outperform SMT models, but they require more data to achieve the best performance. In this thesis, we explore how INR and FDA can also be beneficial to improving NMT models with just a fraction of the available data. On top of that, we propose several improvements for these data-selection methods by exploiting the information on the target side. First, we use the alignment between words in the source and target sides to modify the selection criteria of these methods. Those sentences containing n-grams that are more difficult to translate should be promoted so that more occurrences of these n-grams are selected. Another extension proposed is to select sentences based not on the test set but on an MT-generated approximated translation (so the target-side of the sentences are considered in the selection criteria). Finally, target-language sentences can be translated into the source-language so that INR and FDA have more candidates to select sentences from.
|
|
Keyword:
Computational linguistics; Machine learning; Machine translating
|
|
URL: http://doras.dcu.ie/23726/
|
|
BASE
|
|
Hide details
|
|
3 |
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
|
|
4 |
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
|
|
5 |
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
|
|
6 |
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
|
|
7 |
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)
|
|
BASE
|
|
Show details
|
|
|
|