YerevaNN’s Systems for WMT20 Biomedical Translation Task: The Effect of Fixing Misaligned Sentence Pairs

Karen Hambardzumyan, Hovhannes Tamoyan, Hrant Khachatrian


Abstract
This report describes YerevaNN’s neural machine translation systems and data processing pipelines developed for WMT20 biomedical translation task. We provide systems for English-Russian and English-German language pairs. For the English-Russian pair, our submissions achieve the best BLEU scores, with enru direction outperforming the other systems by a significant margin. We explain most of the improvements by our heavy data preprocessing pipeline which attempts to fix poorly aligned sentences in the parallel data.
Anthology ID:
2020.wmt-1.88
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Editors:
Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Yvette Graham, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
820–825
Language:
URL:
https://aclanthology.org/2020.wmt-1.88
DOI:
Bibkey:
Cite (ACL):
Karen Hambardzumyan, Hovhannes Tamoyan, and Hrant Khachatrian. 2020. YerevaNN’s Systems for WMT20 Biomedical Translation Task: The Effect of Fixing Misaligned Sentence Pairs. In Proceedings of the Fifth Conference on Machine Translation, pages 820–825, Online. Association for Computational Linguistics.
Cite (Informal):
YerevaNN’s Systems for WMT20 Biomedical Translation Task: The Effect of Fixing Misaligned Sentence Pairs (Hambardzumyan et al., WMT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.wmt-1.88.pdf
Optional supplementary material:
 2020.wmt-1.88.OptionalSupplementaryMaterial.tgz
Video:
 https://slideslive.com/38939644