Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder

WonKee Lee, Jaehun Shin, Jong-Hyeok Lee


Abstract
This paper describes POSTECH’s submission to the WMT 2019 shared task on Automatic Post-Editing (APE). In this paper, we propose a new multi-source APE model by extending Transformer. The main contributions of our study are that we 1) reconstruct the encoder to generate a joint representation of translation (mt) and its src context, in addition to the conventional src encoding and 2) suggest two types of multi-source attention layers to compute attention between two outputs of the encoder and the decoder state in the decoder. Furthermore, we train our model by applying various teacher-forcing ratios to alleviate exposure bias. Finally, we adopt the ensemble technique across variations of our model. Experiments on the WMT19 English-German APE data set show improvements in terms of both TER and BLEU scores over the baseline. Our primary submission achieves -0.73 in TER and +1.49 in BLEU compare to the baseline.
Anthology ID:
W19-5412
Volume:
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
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:
112–117
Language:
URL:
https://aclanthology.org/W19-5412
DOI:
10.18653/v1/W19-5412
Bibkey:
Cite (ACL):
WonKee Lee, Jaehun Shin, and Jong-Hyeok Lee. 2019. Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pages 112–117, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder (Lee et al., WMT 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/W19-5412.pdf