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
Venues:
EMNLP | WMT | WS
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
822–826
Language:
URL:
https://www.aclweb.org/anthology/W18-6467
DOI:
10.18653/v1/W18-6467
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-6467.pdf