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
下载
收藏
页码:1683 / 1692
页数:10
相关论文
共 50 条
  • [41] Neural Machine Translation
    Jooste, Wandri
    Haque, Rejwanul
    Way, Andy
    MACHINE TRANSLATION, 2021, 35 (02) : 289 - 299
  • [42] Neural Machine Translation Advised by Statistical Machine Translation
    Wang, Xing
    Lu, Zhengdong
    Tu, Zhaopeng
    Li, Hang
    Xiong, Deyi
    Zhang, Min
    THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 3330 - 3336
  • [43] DEEP: DEnoising Entity Pre-training for Neural Machine Translation
    Hu, Junjie
    Hayashi, Hiroaki
    Cho, Kyunghyun
    Neubig, Graham
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 1753 - 1766
  • [44] Neural Machine Translation as a Novel Approach to Machine Translation
    Benkova, Lucia
    Benko, Lubomir
    DIVAI 2020: 13TH INTERNATIONAL SCIENTIFIC CONFERENCE ON DISTANCE LEARNING IN APPLIED INFORMATICS, 2020, : 499 - 508
  • [45] Training and Inference Methods for High-Coverage Neural Machine Translation
    Yang, Michael
    Liu, Yixin
    Mayuranath, Rahul
    NEURAL GENERATION AND TRANSLATION, 2020, : 119 - 128
  • [46] Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation
    Jiao, Wenxiang
    Wang, Xing
    He, Shilin
    King, Irwin
    Lyu, Michael R.
    Tu, Zhaopeng
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 2255 - 2266
  • [47] Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation
    Xu, Yangyifan
    Liu, Yijin
    Meng, Fandong
    Zhang, Jiajun
    Xu, Jinan
    Zhou, Jie
    ACL-IJCNLP 2021: THE 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 2, 2021, : 511 - 516
  • [48] Neural Name Translation Improves Neural Machine Translation
    Li, Xiaoqing
    Yan, Jinghui
    Zhang, Jiajun
    Zong, Chengqing
    MACHINE TRANSLATION, CWMT 2018, 2019, 954 : 93 - 100
  • [49] Minimum Error-Rate Training in Statistical Machine Translation Using Structural SVMs
    Gonzalez-Rubio, Jesus
    Ortiz-Martinez, Daniel
    Casacuberta, Francisco
    PATTERN RECOGNITION AND IMAGE ANALYSIS, PROCEEDINGS, 2009, 5524 : 378 - +
  • [50] The Event/Machine of Neural Machine Translation?
    Regnauld, Arnaud
    JOURNAL OF AESTHETICS AND PHENOMENOLOGY, 2022, 9 (02) : 141 - 154