MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing

Marcin Junczys-Dowmunt, Roman Grundkiewicz


Abstract
This paper describes the Microsoft and University of Edinburgh submission to the Automatic Post-editing shared task at WMT2018. Based on training data and systems from the WMT2017 shared task, we re-implement our own models from the last shared task and introduce improvements based on extensive parameter sharing. Next we experiment with our implementation of dual-source transformer models and data selection for the IT domain. Our submissions decisively wins the SMT post-editing sub-task establishing the new state-of-the-art and is a very close second (or equal, 16.46 vs 16.50 TER) in the NMT sub-task. Based on the rather weak results in the NMT sub-task, we hypothesize that neural-on-neural APE might not be actually useful.
Anthology ID:
W18-6467
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:
822–826
Language:
URL:
https://aclanthology.org/W18-6467
DOI:
10.18653/v1/W18-6467
Bibkey:
Cite (ACL):
Marcin Junczys-Dowmunt and Roman Grundkiewicz. 2018. MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 822–826, Belgium, Brussels. Association for Computational Linguistics.
Cite (Informal):
MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing (Junczys-Dowmunt & Grundkiewicz, WMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6467.pdf
Data
eSCAPE