Corpus ID: 235613631

Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation

@inproceedings{Kasai2021DeepES,
  title={Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation},
  author={Jungo Kasai and Nikolaos Pappas and Hao Peng and James Cross and Noah A. Smith},
  booktitle={ICLR},
  year={2021}
}
Much recent effort has been invested in non-autoregressive neural machine translation, which appears to be an efficient alternative to state-of-the-art autoregressive machine translation on modern GPUs. In contrast to the latter, where generation is sequential, the former allows generation to be parallelized across target token positions. Some of the latest non-autoregressive models have achieved impressive translation quality-speed tradeoffs compared to autoregressive baselines. In this work… Expand

Figures and Tables from this paper

Finetuning Pretrained Transformers into RNNs
Charformer: Fast Character Transformers via Gradient-based Subword Tokenization
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers
Diversifying Dialog Generation via Adaptive Label Smoothing

References

SHOWING 1-10 OF 66 REFERENCES
...
1
2
3
4
5
...