Addressing the Rare Word Problem in Neural Machine Translation

  title={Addressing the Rare Word Problem in Neural Machine Translation},
  author={Thang Luong and Ilya Sutskever and Quoc V. Le and Oriol Vinyals and Wojciech Zaremba},
Neural Machine Translation (NMT) has recently attracted a l ot of attention due to the very high performance achieved by deep neural network s in other domains. An inherent weakness in existing NMT systems is their inabil ity to correctly translate rare words: end-to-end NMTs tend to have relatively sma ll vocabularies with a single “unknown-word” symbol representing every possibl e out-of-vocabulary (OOV) word. In this paper, we propose and implement a simple t echnique to address this problem… CONTINUE READING
Highly Influential
This paper has highly influenced 54 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 391 citations. REVIEW CITATIONS
277 Citations
26 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 277 extracted citations

392 Citations

Citations per Year
Semantic Scholar estimates that this publication has 392 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…