The University of Edinburgh’s Bengali-Hindi Submissions to the WMT21 News Translation Task

Proyag Pal, Alham Fikri Aji, Pinzhen Chen, Sukanta Sen


Abstract
We describe the University of Edinburgh’s BengaliHindi constrained systems submitted to the WMT21 News Translation task. We submitted ensembles of Transformer models built with large-scale back-translation and fine-tuned on subsets of training data retrieved based on similarity to the target domain.
Anthology ID:
2021.wmt-1.16
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
180–186
Language:
URL:
https://aclanthology.org/2021.wmt-1.16
DOI:
Bibkey:
Cite (ACL):
Proyag Pal, Alham Fikri Aji, Pinzhen Chen, and Sukanta Sen. 2021. The University of Edinburgh’s Bengali-Hindi Submissions to the WMT21 News Translation Task. In Proceedings of the Sixth Conference on Machine Translation, pages 180–186, Online. Association for Computational Linguistics.
Cite (Informal):
The University of Edinburgh’s Bengali-Hindi Submissions to the WMT21 News Translation Task (Pal et al., WMT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2021.wmt-1.16.pdf
Data
CCAligned