Neural Machine Translation of Rare Words with Subword Units

@article{Sennrich2016NeuralMT,
  title={Neural Machine Translation of Rare Words with Subword Units},
  author={Rico Sennrich and B. Haddow and Alexandra Birch},
  journal={ArXiv},
  year={2016},
  volume={abs/1508.07909}
}
Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this paper, we introduce a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units. This is based on the intuition that various word classes are translatable via… Expand
Finding Better Subword Segmentation for Neural Machine Translation
A Latent Morphology Model for Open-Vocabulary Neural Machine Translation
An Evaluation of Two Vocabulary Reduction Methods for Neural Machine Translation
Factored Neural Machine Translation
Explicitly Modeling Word Translations in Neural Machine Translation
Neural Name Translation Improves Neural Machine Translation
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 53 REFERENCES
Addressing the Rare Word Problem in Neural Machine Translation
Variable-Length Word Encodings for Neural Translation Models
Character-based Neural Machine Translation
On Using Very Large Target Vocabulary for Neural Machine Translation
Effective Approaches to Attention-based Neural Machine Translation
Recurrent Continuous Translation Models
...
1
2
3
4
5
...