EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT

Svetlana Tchistiakova, Jesujoba Alabi, Koel Dutta Chowdhury, Sourav Dutta, Dana Ruiter


Abstract
We describe the EdinSaar submission to the shared task of Multilingual Low-Resource Translation for North Germanic Languages at the Sixth Conference on Machine Translation (WMT2021). We submit multilingual translation models for translations to/from Icelandic (is), Norwegian-Bokmal (nb), and Swedish (sv). We employ various experimental approaches, including multilingual pre-training, back-translation, fine-tuning, and ensembling. In most translation directions, our models outperform other submitted systems.
Anthology ID:
2021.wmt-1.44
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:
368–375
Language:
URL:
https://aclanthology.org/2021.wmt-1.44
DOI:
Bibkey:
Cite (ACL):
Svetlana Tchistiakova, Jesujoba Alabi, Koel Dutta Chowdhury, Sourav Dutta, and Dana Ruiter. 2021. EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT. In Proceedings of the Sixth Conference on Machine Translation, pages 368–375, Online. Association for Computational Linguistics.
Cite (Informal):
EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT (Tchistiakova et al., WMT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.wmt-1.44.pdf