The University of Helsinki Submissions to the WMT19 Similar Language Translation Task

Yves Scherrer, Raúl Vázquez, Sami Virpioja


Abstract
This paper describes the University of Helsinki Language Technology group’s participation in the WMT 2019 similar language translation task. We trained neural machine translation models for the language pairs Czech <-> Polish and Spanish <-> Portuguese. Our experiments focused on different subword segmentation methods, and in particular on the comparison of a cognate-aware segmentation method, Cognate Morfessor, with character segmentation and unsupervised segmentation methods for which the data from different languages were simply concatenated. We did not observe major benefits from cognate-aware segmentation methods, but further research may be needed to explore larger parts of the parameter space. Character-level models proved to be competitive for translation between Spanish and Portuguese, but they are slower in training and decoding.
Anthology ID:
W19-5432
Volume:
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
Month:
August
Year:
2019
Address:
Florence, Italy
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
236–244
Language:
URL:
https://aclanthology.org/W19-5432
DOI:
10.18653/v1/W19-5432
Bibkey:
Cite (ACL):
Yves Scherrer, Raúl Vázquez, and Sami Virpioja. 2019. The University of Helsinki Submissions to the WMT19 Similar Language Translation Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pages 236–244, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
The University of Helsinki Submissions to the WMT19 Similar Language Translation Task (Scherrer et al., WMT 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5432.pdf