From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots

@inproceedings{Chen2019FromWT,
  title={From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots},
  author={Shizhe Chen and Q. Jin and J. Fu},
  booktitle={IJCAI},
  year={2019}
}
  • Shizhe Chen, Q. Jin, J. Fu
  • Published in IJCAI 2019
  • Computer Science
  • The neural machine translation model has suffered from the lack of large-scale parallel corpora. In contrast, we humans can learn multi-lingual translations even without parallel texts by referring our languages to the external world. To mimic such human learning behavior, we employ images as pivots to enable zero-resource translation learning. However, a picture tells a thousand words, which makes multi-lingual sentences pivoted by the same image noisy as mutual translations and thus hinders… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES
    Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
    808
    Zero-resource machine translation by multimodal encoder–decoder network with multimedia pivot
    31
    Phrase-Based & Neural Unsupervised Machine Translation
    293
    Unsupervised Bilingual Lexicon Induction from Mono-lingual Multimodal Data
    5
    Unsupervised Neural Machine Translation
    381
    Neural Machine Translation of Rare Words with Subword Units
    2577
    Transfer Learning for Low-Resource Neural Machine Translation
    312
    Neural Machine Translation by Jointly Learning to Align and Translate
    12528
    Unsupervised Multi-Modal Neural Machine Translation
    7