The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks

Yves Scherrer, Stig-Arne Grönroos, Sami Virpioja


Abstract
This paper describes the joint participation of University of Helsinki and Aalto University to two shared tasks of WMT 2020: the news translation between Inuktitut and English and the low-resource translation between German and Upper Sorbian. For both tasks, our efforts concentrate on efficient use of monolingual and related bilingual corpora with scheduled multi-task learning as well as an optimized subword segmentation with sampling. Our submission obtained the highest score for Upper Sorbian -> German and was ranked second for German -> Upper Sorbian according to BLEU scores. For English–Inuktitut, we reached ranks 8 and 10 out of 11 according to BLEU scores.
Anthology ID:
2020.wmt-1.134
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:
1129–1138
Language:
URL:
https://aclanthology.org/2020.wmt-1.134
DOI:
Bibkey:
Cite (ACL):
Yves Scherrer, Stig-Arne Grönroos, and Sami Virpioja. 2020. The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks. In Proceedings of the Fifth Conference on Machine Translation, pages 1129–1138, Online. Association for Computational Linguistics.
Cite (Informal):
The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks (Scherrer et al., WMT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2020.wmt-1.134.pdf
Video:
 https://slideslive.com/38939589