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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationWAT 2020 - 7th Workshop on Asian Translation, Proceedings
EditorsToshiaki Nakazawa, Hideki Nakayama, Chenchen Ding, Raj Dabre, Anoop Kunchukuttan, Win Pa Pa, Ondrej Bojar, Shantipriya Parida, Isao Goto, Hidaya Mino, Hiroshi Manabe, Katsuhito Sudoh, Sadao Kurohashi, Pushpak Bhattacharyya
PublisherAssociation for Computational Linguistics (ACL)
Pages64-71
Number of pages8
ISBN (Electronic)9781952148958
StatePublished - 2020
Event7th Workshop on Asian Translation, WAT 2020 - Suzhou, China
Duration: 4 Dec 2020 → …

Publication series

NameWAT 2020 - 7th Workshop on Asian Translation, Proceedings

Conference

Conference7th Workshop on Asian Translation, WAT 2020
Country/TerritoryChina
CitySuzhou
Period4/12/20 → …

Cite this