Corpus ID: 4720016

Fast Decoding in Sequence Models using Discrete Latent Variables

@inproceedings{Kaiser2018FastDI,
  title={Fast Decoding in Sequence Models using Discrete Latent Variables},
  author={Łukasz Kaiser and Aurko Roy and Ashish Vaswani and Niki Parmar and S. Bengio and Jakob Uszkoreit and Noam M. Shazeer},
  booktitle={ICML},
  year={2018}
}
Autoregressive sequence models based on deep neural networks, such as RNNs, Wavenet and the Transformer attain state-of-the-art results on many tasks. [...] Key Method We first auto-encode the target sequence into a shorter sequence of discrete latent variables, which at inference time is generated autoregressively, and finally decode the output sequence from this shorter latent sequence in parallel.Expand
Blockwise Parallel Decoding for Deep Autoregressive Models
Fast Structured Decoding for Sequence Models
Theory and Experiments on Vector Quantized Autoencoders
Towards a better understanding of Vector Quantized Autoencoders
STCN: Stochastic Temporal Convolutional Networks
Semi-Autoregressive Neural Machine Translation
Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 51 REFERENCES
Discrete Autoencoders for Sequence Models
Neural Machine Translation in Linear Time
Sequence to Sequence Learning with Neural Networks
Attention is All you Need
Convolutional Sequence to Sequence Learning
Generating Sentences from a Continuous Space
Neural Discrete Representation Learning
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Compressing Word Embeddings via Deep Compositional Code Learning
...
1
2
3
4
5
...