Multi-encoder Transformer Network for Automatic Post-Editing

Jaehun Shin, Jong-Hyeok Lee


Abstract
This paper describes the POSTECH’s submission to the WMT 2018 shared task on Automatic Post-Editing (APE). We propose a new neural end-to-end post-editing model based on the transformer network. We modified the encoder-decoder attention to reflect the relation between the machine translation output, the source and the post-edited translation in APE problem. Experiments on WMT17 English-German APE data set show an improvement in both TER and BLEU score over the best result of WMT17 APE shared task. Our primary submission achieves -4.52 TER and +6.81 BLEU score on PBSMT task and -0.13 TER and +0.40 BLEU score for NMT task compare to the baseline.
Anthology ID:
W18-6470
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:
840–845
Language:
URL:
https://aclanthology.org/W18-6470
DOI:
10.18653/v1/W18-6470
Bibkey:
Cite (ACL):
Jaehun Shin and Jong-Hyeok Lee. 2018. Multi-encoder Transformer Network for Automatic Post-Editing. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 840–845, Belgium, Brussels. Association for Computational Linguistics.
Cite (Informal):
Multi-encoder Transformer Network for Automatic Post-Editing (Shin & Lee, WMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6470.pdf