The University of Edinburgh’s English-German and English-Hausa Submissions to the WMT21 News Translation Task

Pinzhen Chen, Jindřich Helcl, Ulrich Germann, Laurie Burchell, Nikolay Bogoychev, Antonio Valerio Miceli Barone, Jonas Waldendorf, Alexandra Birch, Kenneth Heafield


Abstract
This paper presents the University of Edinburgh’s constrained submissions of English-German and English-Hausa systems to the WMT 2021 shared task on news translation. We build En-De systems in three stages: corpus filtering, back-translation, and fine-tuning. For En-Ha we use an iterative back-translation approach on top of pre-trained En-De models and investigate vocabulary embedding mapping.
Anthology ID:
2021.wmt-1.4
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Venues:
EMNLP | WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
104–109
Language:
URL:
https://aclanthology.org/2021.wmt-1.4
DOI:
Bibkey:
Cite (ACL):
Pinzhen Chen, Jindřich Helcl, Ulrich Germann, Laurie Burchell, Nikolay Bogoychev, Antonio Valerio Miceli Barone, Jonas Waldendorf, Alexandra Birch, and Kenneth Heafield. 2021. The University of Edinburgh’s English-German and English-Hausa Submissions to the WMT21 News Translation Task. In Proceedings of the Sixth Conference on Machine Translation, pages 104–109, Online. Association for Computational Linguistics.
Cite (Informal):
The University of Edinburgh’s English-German and English-Hausa Submissions to the WMT21 News Translation Task (Chen et al., WMT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.wmt-1.4.pdf
Code
 marian-nmt/marian
Data
ParaCrawl