• Published 2020

NEURAL MACHINE TRANSLATION

@inproceedings{Zhu2020NEURALMT,
  title={NEURAL MACHINE TRANSLATION},
  author={Jinhua Zhu and Yingce Xia and Lijun Wu and Di He and Tao Qin and Wengang Zhou and Houqiang Li and Tie-Yan Liu},
  year={2020}
}
The recently proposed BERT (Devlin et al., 2019) has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks enough exploration. While BERT is more commonly used as fine-tuning instead of contextual embedding for downstream language understanding tasks, in NMT, our preliminary exploration of using BERT as contextual embedding is better than… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 42 REFERENCES

Cross-lingual Language Model Pretraining

VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Deep contextualized word representations

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Attention is All you Need

VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

Improving Language Understanding by Generative Pre-Training

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Scaling Neural Machine Translation

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL