The University of Helsinki submissions to the WMT18 news task

Alessandro Raganato, Yves Scherrer, Tommi Nieminen, Arvi Hurskainen, Jörg Tiedemann


Abstract
This paper describes the University of Helsinki’s submissions to the WMT18 shared news translation task for English-Finnish and English-Estonian, in both directions. This year, our main submissions employ a novel neural architecture, the Transformer, using the open-source OpenNMT framework. Our experiments couple domain labeling and fine tuned multilingual models with shared vocabularies between the source and target language, using the provided parallel data of the shared task and additional back-translations. Finally, we compare, for the English-to-Finnish case, the effectiveness of different machine translation architectures, starting from a rule-based approach to our best neural model, analyzing the output and highlighting future research.
Anthology ID:
W18-6425
Volume:
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Month:
October
Year:
2018
Address:
Belgium, Brussels
Editors:
Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Lucia Specia, Marco Turchi, Karin Verspoor
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
488–495
Language:
URL:
https://aclanthology.org/W18-6425
DOI:
10.18653/v1/W18-6425
Bibkey:
Cite (ACL):
Alessandro Raganato, Yves Scherrer, Tommi Nieminen, Arvi Hurskainen, and Jörg Tiedemann. 2018. The University of Helsinki submissions to the WMT18 news task. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 488–495, Belgium, Brussels. Association for Computational Linguistics.
Cite (Informal):
The University of Helsinki submissions to the WMT18 news task (Raganato et al., WMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6425.pdf
Data
WMT 2018