Corpus ID: 3645288

Joint Training for Neural Machine Translation Models with Monolingual Data

@article{Zhang2018JointTF,
  title={Joint Training for Neural Machine Translation Models with Monolingual Data},
  author={Zhirui Zhang and Shujie Liu and Mu Li and Ming Zhou and Enhong Chen},
  journal={ArXiv},
  year={2018},
  volume={abs/1803.00353}
}
  • Zhirui Zhang, Shujie Liu, +2 authors Enhong Chen
  • Published in AAAI 2018
  • Computer Science
  • Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation tasks where parallel data are not rich enough. In this paper, we propose a novel approach to better leveraging monolingual data for neural machine translation by jointly learning source-to-target and target-to-source NMT models for a language pair with a joint EM… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 35 CITATIONS

    Mirror-Generative Neural Machine Translation

    VIEW 12 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    MIRROR-GENERATIVE NEURAL MACHINE TRANSLA-

    • 2019
    VIEW 12 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Language Model-Driven Unsupervised Neural Machine Translation

    VIEW 6 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Semi-Supervised Neural Machine Translation via Marginal Distribution Estimation

    • Yijun Wang, Yingce Xia, +4 authors Tie-Yan Liu
    • Computer Science
    • IEEE/ACM Transactions on Audio, Speech, and Language Processing
    • 2019
    VIEW 4 EXCERPTS
    CITES METHODS, BACKGROUND & RESULTS

    Triangular Architecture for Rare Language Translation

    VIEW 6 EXCERPTS
    CITES BACKGROUND, RESULTS & METHODS

    Baidu Neural Machine Translation Systems for WMT19

    VIEW 2 EXCERPTS
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES

    Semi-Supervised Learning for Neural Machine Translation

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural Machine Translation by Jointly Learning to Align and Translate

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    On the difficulty of training recurrent neural networks

    VIEW 1 EXCERPT
    HIGHLY INFLUENTIAL

    Understanding the difficulty of training deep feedforward neural networks

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Dual Learning for Machine Translation

    VIEW 1 EXCERPT