JHU 2019 Robustness Task System Description

Matt Post, Kevin Duh


Abstract
We describe the JHU submissions to the French–English, Japanese–English, and English–Japanese Robustness Task at WMT 2019. Our goal was to evaluate the performance of baseline systems on both the official noisy test set as well as news data, in order to ensure that performance gains in the latter did not come at the expense of general-domain performance. To this end, we built straightforward 6-layer Transformer models and experimented with a handful of variables including subword processing (FR→EN) and a handful of hyperparameters settings (JA↔EN). As expected, our systems performed reasonably.
Anthology ID:
W19-5366
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:
552–558
Language:
URL:
https://aclanthology.org/W19-5366
DOI:
10.18653/v1/W19-5366
Bibkey:
Cite (ACL):
Matt Post and Kevin Duh. 2019. JHU 2019 Robustness Task System Description. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 552–558, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
JHU 2019 Robustness Task System Description (Post & Duh, WMT 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5366.pdf
Data
MTNT