Iterative Back-Translation for Neural Machine Translation

被引：0
|
作者：
Vu Cong Duy Hoang [1 ]
Koehn, Philipp [2 ]
Haffari, Gholamreza [3 ]
Cohn, Trevor [1 ]
机构：
[1] Univ Melbourne, Comp & Informat Syst, Melbourne, Vic, Australia
[2] Johns Hopkins Univ, Comp Sci Dept, Baltimore, MD 21218 USA
[3] Monash Univ, Fac Informat Technol, Clayton, Vic, Australia
来源：
NEURAL MACHINE TRANSLATION AND GENERATION | 2018年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems. Our proposed method is very simple yet effective and highly applicable in practice. We demonstrate improvements in neural machine translation quality in both high and low resourced scenarios, including the best reported BLEU scores for the WMT 2017 German <-> English tasks.
引用
收藏
页码：18 / 24
页数：7
相关论文
共 50 条
  • [1] Generalizing Back-Translation in Neural Machine Translation
    Graca, Miguel
    Kim, Yunsu
    Schamper, Julian
    Khadivi, Shahram
    Ney, Hermann
    [J]. FOURTH CONFERENCE ON MACHINE TRANSLATION (WMT 2019), VOL 1: RESEARCH PAPERS, 2019, : 45 - 52
  • [2] Back-Translation Sampling by Targeting DifficultWords in Neural Machine Translation
    Fadaee, Marzieh
    Monz, Christof
    [J]. 2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 436 - 446
  • [3] Neural Machine Translation Based on Back-Translation for Multilingual Translation Evaluation Task
    Lai, Siyu
    Yang, Yueting
    Xu, Jin'an
    Chen, Yufeng
    Huang, Hui
    [J]. MACHINE TRANSLATION, CCMT 2020, 2020, 1328 : 132 - 141
  • [4] Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
    Wu, Jiawei
    Wang, Xin
    Wang, William Yang
    [J]. 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 1173 - 1183
  • [5] On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation
    Liu, Xuebo
    Wang, Longyue
    Wong, Derek F.
    Ding, Liang
    Chao, Lidia S.
    Shi, Shuming
    Tu, Zhaopeng
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 2900 - 2907
  • [6] On The Evaluation of Machine Translation Systems Trained With Back-Translation
    Edunov, Sergey
    Ott, Myle
    Ranzato, Marc'Aurelio
    Auli, Michael
    [J]. 58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), 2020, : 2836 - 2846
  • [7] Iterative Domain-Repaired Back-Translation
    Wei, Hao-Ran
    Zhang, Zhirui
    Chen, Boxing
    Luo, Weihua
    [J]. PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 5884 - 5893
  • [8] Back-translation in Translation Teaching
    刘聪
    [J]. 读与写(教育教学刊), 2018, 15 (10) : 3 - 3
  • [9] A Joint Back-Translation and Transfer Learning Method for Low-Resource Neural Machine Translation
    Luo, Gong-Xu
    Yang, Ya-Ting
    Dong, Rui
    Chen, Yan-Hong
    Zhang, Wen-Bo
    [J]. MATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020
  • [10] Enhancement of English-Bengali Machine Translation Leveraging Back-Translation
    Mondal, Subrota Kumar
    Wang, Chengwei
    Chen, Yijun
    Cheng, Yuning
    Huang, Yanbo
    Dai, Hong-Ning
    Kabir, H. M. Dipu
    [J]. APPLIED SCIENCES-BASEL, 2024, 14 (15):
12345