Exploiting Source-side Monolingual Data in Neural Machine Translation

@inproceedings{Zhang2016ExploitingSM,
  title={Exploiting Source-side Monolingual Data in Neural Machine Translation},
  author={Jiajun Zhang and Chengqing Zong},
  booktitle={EMNLP},
  year={2016}
}
Neural Machine Translation (NMT) based on the encoder-decoder architecture has recently become a new paradigm. Researchers have proven that the target-side monolingual data can greatly enhance the decoder model of NMT. However, the source-side monolingual data is not fully explored although it should be useful to strengthen the encoder model of NMT, especially when the parallel corpus is far from sufficient. In this paper, we propose two approaches to make full use of the sourceside monolingual… CONTINUE READING
Highly Cited
This paper has 62 citations. REVIEW CITATIONS
46 Citations
38 References
Similar Papers

Citations

Publications citing this paper.

62 Citations

02040201620172018
Citations per Year
Semantic Scholar estimates that this publication has 62 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 38 references

Similar Papers

Loading similar papers…