跳到主要导航 跳到搜索 跳到主要内容

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
  • Kyoto University
  • East China Normal University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

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.

源语言英语
主期刊名WAT 2020 - 7th Workshop on Asian Translation, Proceedings
编辑Toshiaki 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
出版商Association for Computational Linguistics (ACL)
64-71
页数8
ISBN(电子版)9781952148958
出版状态已出版 - 2020
活动7th Workshop on Asian Translation, WAT 2020 - Suzhou, 中国
期限: 4 12月 2020 → …

出版系列

姓名WAT 2020 - 7th Workshop on Asian Translation, Proceedings

会议

会议7th Workshop on Asian Translation, WAT 2020
国家/地区中国
Suzhou
时期4/12/20 → …

引用此