Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings

@inproceedings{Dou2019UnsupervisedDA,
  title={Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings},
  author={Zi-Yi Dou and J. Hu and Antonios Anastasopoulos and Graham Neubig},
  booktitle={EMNLP/IJCNLP},
  year={2019}
}
  • Zi-Yi Dou, J. Hu, +1 author Graham Neubig
  • Published in EMNLP/IJCNLP 2019
  • Computer Science
  • The recent success of neural machine translation models relies on the availability of high quality, in-domain data. Domain adaptation is required when domain-specific data is scarce or nonexistent. Previous unsupervised domain adaptation strategies include training the model with in-domain copied monolingual or back-translated data. However, these methods use generic representations for text regardless of domain shift, which makes it infeasible for translation models to control outputs… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 28 REFERENCES
    A Survey of Domain Adaptation for Neural Machine Translation
    75
    Multi-Domain Neural Machine Translation through Unsupervised Adaptation
    45
    Domain Control for Neural Machine Translation
    73
    Domain Adaptation via Pseudo In-Domain Data Selection
    433
    Fast Domain Adaptation for Neural Machine Translation
    102
    Non-Parametric Adaptation for Neural Machine Translation
    14
    An Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation
    89