CUNI System for the WMT19 Robustness Task

Jindřich Helcl, Jindřich Libovický, Martin Popel


Abstract
We present our submission to the WMT19 Robustness Task. Our baseline system is the Charles University (CUNI) Transformer system trained for the WMT18 shared task on News Translation. Quantitative results show that the CUNI Transformer system is already far more robust to noisy input than the LSTM-based baseline provided by the task organizers. We further improved the performance of our model by fine-tuning on the in-domain noisy data without influencing the translation quality on the news domain.
Anthology ID:
W19-5364
Volume:
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Marco Turchi, Karin Verspoor
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
539–543
Language:
URL:
https://aclanthology.org/W19-5364
DOI:
10.18653/v1/W19-5364
Bibkey:
Cite (ACL):
Jindřich Helcl, Jindřich Libovický, and Martin Popel. 2019. CUNI System for the WMT19 Robustness Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 539–543, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
CUNI System for the WMT19 Robustness Task (Helcl et al., WMT 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/W19-5364.pdf
Data
MTNTWMT 2014