Nayak, Prashanth, Haque, Rejwanul ORCID: 0000-0003-1680-0099 and Way, Andy ORCID: 0000-0001-5736-5930 (2020) The ADAPT centre’s participation in WAT 2020 English-to-Odia translation task. In: WAT2020 :The 7th Workshop on Asian Translation, 4-7 Dec 2020, Suzhou, China (Online).
Abstract
This paper describes the ADAPT Centre submissions to WAT 2020 for the English-to-Odia translation task. We present the approaches that we followed to try to build competitive machine translation (MT) systems for English-to-Odia. Our approaches include monolingual data selection for creating synthetic data and identifying optimal sets of hyperparameters for Transformer in a low-resource scenario. Our best MT system produces 4.96
BLEU points on the evaluation test set in the English-to-Odia translation task
Metadata
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Event Type: | Workshop |
Refereed: | Yes |
Subjects: | Computer Science > Computational linguistics Computer Science > Machine learning |
DCU Faculties and Centres: | DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing Research Initiatives and Centres > ADAPT |
Published in: | Proceedings of the 7th Workshop on Asian Translation (WAT2020). . Association for Computational Linguistics (ACL). |
Publisher: | Association for Computational Linguistics (ACL) |
Official URL: | https://www.aclweb.org/anthology/2020.wat-1.17/ |
Copyright Information: | © 2020 The Authors (CC-BY-4.0) |
Funders: | Science Foundation Ireland (SFI) Research Centres Programme (Grant No. 13/RC/2106), European Regional Development Fund, European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 713567, Science Foundation Ireland (SFI) Grant Number 13/RC/2077 and 18/CRT/6224 . |
ID Code: | 25462 |
Deposited On: | 08 Feb 2021 11:28 by Prashanth Nayak . Last Modified 08 Feb 2021 11:28 |
Documents
Full text available as:
Preview |
PDF
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
81kB |
Downloads
Downloads
Downloads per month over past year
Archive Staff Only: edit this record