Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen’s Submission to WMT-2020

Prajit Dhar, Arianna Bisazza, Gertjan van Noord


Abstract
This paper describes our submission for the English-Tamil news translation task of WMT-2020. The various techniques and Neural Machine Translation (NMT) models used by our team are presented and discussed, including back-translation, fine-tuning and word dropout. Additionally, our experiments show that using a linguistically motivated subword segmentation technique (Ataman et al., 2017) does not consistently outperform the more widely used, non-linguistically motivated SentencePiece algorithm (Kudo and Richardson, 2018), despite the agglutinative nature of Tamil morphology.
Anthology ID:
2020.wmt-1.9
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
126–133
Language:
URL:
https://aclanthology.org/2020.wmt-1.9
DOI:
Bibkey:
Cite (ACL):
Prajit Dhar, Arianna Bisazza, and Gertjan van Noord. 2020. Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen’s Submission to WMT-2020. In Proceedings of the Fifth Conference on Machine Translation, pages 126–133, Online. Association for Computational Linguistics.
Cite (Informal):
Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen’s Submission to WMT-2020 (Dhar et al., WMT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.wmt-1.9.pdf
Video:
 https://slideslive.com/38939635