Corpus ID: 209862279

Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation

@article{Pan2020MorphologicalWS,
  title={Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation},
  author={Yirong Pan and X. Li and Y. Yang and Rui Dong},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.01589}
}
  • Yirong Pan, X. Li, +1 author Rui Dong
  • Published 2020
  • Computer Science
  • ArXiv
  • Neural machine translation (NMT) has achieved impressive performance on machine translation task in recent years. However, in consideration of efficiency, a limited-size vocabulary that only contains the top-N highest frequency words are employed for model training, which leads to many rare and unknown words. It is rather difficult when translating from the low-resource and morphologically-rich agglutinative languages, which have complex morphology and large vocabulary. In this paper, we… CONTINUE READING
    Multi-Task Neural Model for Agglutinative Language Translation
    Sequence Generation with Mixed Representations
    1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 22 REFERENCES
    Target-side Word Segmentation Strategies for Neural Machine Translation
    25
    Neural Machine Translation of Rare Words with Subword Units
    2579
    On Using Very Large Target Vocabulary for Neural Machine Translation
    714
    Improving Neural Machine Translation Models with Monolingual Data
    878
    Neural Machine Translation by Jointly Learning to Align and Translate
    12533
    Effective Approaches to Attention-based Neural Machine Translation
    3807