Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models

@article{Luong2016AchievingOV,
  title={Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models},
  author={Minh-Thang Luong and Christopher D. Manning},
  journal={CoRR},
  year={2016},
  volume={abs/1604.00788}
}
Nearly all previous work in neural machine translation (NMT) has used quite restricted vocabularies, perhaps with a subsequent method to patch in unknown words. This paper presents a novel wordcharacter solution to achieving open vocabulary NMT. We build hybrid systems that translate mostly at theword level and consult thecharactercomponents for rare words… CONTINUE READING

8 Figures & Tables

Topics

Statistics

050201620172018
Citations per Year

169 Citations

Semantic Scholar estimates that this publication has 169 citations based on the available data.

See our FAQ for additional information.