Minimum Risk Training for Neural Machine Translation

被引:0
|
作者
Shen, Shiqi [1 ]
Cheng, Yong [2 ]
He, Zhongjun [3 ]
He, Wei [3 ]
Wu, Hua [3 ]
Sun, Maosong [1 ]
Liu, Yang [1 ]
机构
[1] Tsinghua Univ, Dept Comp Sci & Technol, Tsinghua Natl Lab Informat Sci & Technol, State Key Lab Intelligent Technol & Syst, Beijing, Peoples R China
[2] Tsinghua Univ, Inst Interdisciplinary Informat Sci, Beijing, Peoples R China
[3] Baidu Inc, Beijing, Peoples R China
基金
中国国家自然科学基金; 新加坡国家研究基金会;
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 propose minimum risk training for end-to-end neural machine translation. Unlike conventional maximum likelihood estimation, minimum risk training is capable of optimizing model parameters directly with respect to arbitrary evaluation metrics, which are not necessarily differentiable. Experiments show that our approach achieves significant improvements over maximum likelihood estimation on a state-of-the-art neural machine translation system across various languages pairs. Transparent to architectures, our approach can be applied to more neural networks and potentially benefit more NLP tasks.
引用
收藏
页码:1683 / 1692
页数:10
相关论文
共 50 条
  • [31] Training with Additional Semantic Constraints for Enhancing Neural Machine Translation
    Ji, Yatu
    Hou, Hongxu
    Chen, Junjie
    Wu, Nier
    PRICAI 2019: TRENDS IN ARTIFICIAL INTELLIGENCE, PT I, 2019, 11670 : 300 - 313
  • [32] Synthetic Pre-Training Tasks for Neural Machine Translation
    He, Zexue
    Blackwood, Graeme
    Panda, Rameswar
    McAuley, Julian
    Feris, Rogerio
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023), 2023, : 8080 - 8098
  • [33] Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation
    Wang, Rui
    Utiyama, Masao
    Sumita, Eiichiro
    PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2, 2018, : 298 - 304
  • [34] Multilingual Denoising Pre-training for Neural Machine Translation
    Liu, Yinhan
    Gu, Jiatao
    Goyal, Naman
    Li, Xian
    Edunov, Sergey
    Ghazvininejad, Marjan
    Lewis, Mike
    Zettlemoyer, Luke
    TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2020, 8 : 726 - 742
  • [35] ZeUS: An Unified Training Framework for Constrained Neural Machine Translation
    Yang, Murun
    IEEE ACCESS, 2024, 12 : 124695 - 124704
  • [36] Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
    Wieting, John
    Berg-Kirkpatrick, Taylor
    Gimpel, Kevin
    Neubig, Graham
    57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 4344 - 4355
  • [37] Bridging the Gap between Training and Inference for Neural Machine Translation
    Zhang, Wen
    Feng, Yang
    Meng, Fandong
    You, Di
    Liu, Qun
    57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 4334 - 4343
  • [38] Joint Training for Neural Machine Translation Models with Monolingual Data
    Zhang, Zhirui
    Liu, Shujie
    Li, Mu
    Zhou, Ming
    Chen, Enhong
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 555 - 562
  • [39] 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
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 2900 - 2907
  • [40] Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios
    Sun, Haipeng
    Wang, Rui
    Chen, Kehai
    Utiyama, Masao
    Sumita, Eiichiro
    Zhao, Tiejun
    2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 3975 - 3981