Meta Ensemble for Japanese-Chinese Neural Machine Translation: Kyoto-U+ECNU Participation to WAT 2020

Zhuoyuan Mao, Yibin Shen, Chenhui Chu, Sadao Kurohashi, Cheqing Jin


Abstract
This paper describes the Japanese-Chinese Neural Machine Translation (NMT) system submitted by the joint team of Kyoto University and East China Normal University (Kyoto-U+ECNU) to WAT 2020 (Nakazawa et al.,2020). We participate in APSEC Japanese-Chinese translation task. We revisit several techniques for NMT including various architectures, different data selection and augmentation methods, denoising pre-training, and also some specific tricks for Japanese-Chinese translation. We eventually perform a meta ensemble to combine all of the models into a single model. BLEU results of this meta ensembled model rank the first both on 2 directions of ASPEC Japanese-Chinese translation.
Anthology ID:
2020.wat-1.5
Volume:
Proceedings of the 7th Workshop on Asian Translation
Month:
December
Year:
2020
Address:
Suzhou, China
Venue:
WAT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
64–71
Language:
URL:
https://aclanthology.org/2020.wat-1.5
DOI:
Bibkey:
Cite (ACL):
Zhuoyuan Mao, Yibin Shen, Chenhui Chu, Sadao Kurohashi, and Cheqing Jin. 2020. Meta Ensemble for Japanese-Chinese Neural Machine Translation: Kyoto-U+ECNU Participation to WAT 2020. In Proceedings of the 7th Workshop on Asian Translation, pages 64–71, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Meta Ensemble for Japanese-Chinese Neural Machine Translation: Kyoto-U+ECNU Participation to WAT 2020 (Mao et al., WAT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.wat-1.5.pdf
Data
ASPECOpenSubtitlesWikiMatrix