The IICT-Yverdon System for the WMT 2021 Unsupervised MT and Very Low Resource Supervised MT Task

Àlex R. Atrio, Gabriel Luthier, Axel Fahy, Giorgos Vernikos, Andrei Popescu-Belis, Ljiljana Dolamic


Abstract
In this paper, we present the systems submitted by our team from the Institute of ICT (HEIG-VD / HES-SO) to the Unsupervised MT and Very Low Resource Supervised MT task. We first study the improvements brought to a baseline system by techniques such as back-translation and initialization from a parent model. We find that both techniques are beneficial and suffice to reach performance that compares with more sophisticated systems from the 2020 task. We then present the application of this system to the 2021 task for low-resource supervised Upper Sorbian (HSB) to German translation, in both directions. Finally, we present a contrastive system for HSB-DE in both directions, and for unsupervised German to Lower Sorbian (DSB) translation, which uses multi-task training with various training schedules to improve over the baseline.
Anthology ID:
2021.wmt-1.103
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:
973–981
Language:
URL:
https://aclanthology.org/2021.wmt-1.103
DOI:
Bibkey:
Cite (ACL):
Àlex R. Atrio, Gabriel Luthier, Axel Fahy, Giorgos Vernikos, Andrei Popescu-Belis, and Ljiljana Dolamic. 2021. The IICT-Yverdon System for the WMT 2021 Unsupervised MT and Very Low Resource Supervised MT Task. In Proceedings of the Sixth Conference on Machine Translation, pages 973–981, Online. Association for Computational Linguistics.
Cite (Informal):
The IICT-Yverdon System for the WMT 2021 Unsupervised MT and Very Low Resource Supervised MT Task (Atrio et al., WMT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wmt-1.103.pdf
Data
WMT 2020