Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

@article{Johnson2017GooglesMN,
  title={Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation},
  author={Melvin Johnson and Mike Schuster and Quoc V. Le and Maxim Krikun and Yonghui Wu and Zhifeng Chen and Nikhil Thorat and Fernanda B. Vi{\'e}gas and Martin Wattenberg and Gregory S. Corrado and Macduff Hughes and Jeffrey Dean},
  journal={TACL},
  year={2017},
  volume={5},
  pages={339-351}
}
We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no changes to the model architecture from a standard NMT system but instead introduces an artificial token at the beginning of the input sentence to specify the required target language. The rest of the model, which includes an encoder, decoder and attention module, remains unchanged and is shared across all languages. Using a shared wordpiece… CONTINUE READING
Highly Influential
This paper has highly influenced 31 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 651 citations. REVIEW CITATIONS
172 Citations
33 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 172 extracted citations

652 Citations

0200400201620172018
Citations per Year
Semantic Scholar estimates that this publication has 652 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 33 references

Similar Papers

Loading similar papers…