Corpus ID: 15816492

The Neural Noisy Channel

@article{Yu2017TheNN,
  title={The Neural Noisy Channel},
  author={L. Yu and P. Blunsom and Chris Dyer and Edward Grefenstette and Tom{\'a}s Kocisk{\'y}},
  journal={ArXiv},
  year={2017},
  volume={abs/1611.02554}
}
We formulate sequence to sequence transduction as a noisy channel decoding problem and use recurrent neural networks to parameterise the source and channel models. [...] Key Method Using a latent variable to control how much of the conditioning sequence the channel model needs to read in order to generate a subsequent symbol, we obtain a tractable and effective beam search decoder. Experimental results on abstractive sentence summarisation, morphological inflection, and machine translation show that noisy…Expand
46 Citations
Simple and Effective Noisy Channel Modeling for Neural Machine Translation
  • 26
  • Highly Influenced
  • PDF
Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling
  • Highly Influenced
  • PDF
Learning to Write with Cooperative Discriminators
  • 86
  • Highly Influenced
  • PDF
Pretraining the Noisy Channel Model for Task-Oriented Dialogue
  • PDF
Stochasticity and Non-Autoregressive Modeling in Deep Generative Models of Text
Online and Linear-Time Attention by Enforcing Monotonic Alignments
  • 126
  • PDF
Neural Phrase-to-Phrase Machine Translation
  • 10
  • PDF
Putting Machine Translation in Context with the Noisy Channel Model
  • 6
  • PDF
Structured Attention Networks
  • 244
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 52 REFERENCES
Online Segment to Segment Neural Transduction
  • 69
  • PDF
Segmental Recurrent Neural Networks
  • 101
  • PDF
Sequence Transduction with Recurrent Neural Networks
  • A. Graves
  • Computer Science, Mathematics
  • ArXiv
  • 2012
  • 672
  • PDF
Sequence to Sequence Learning with Neural Networks
  • 12,163
  • PDF
A Neural Transducer
  • 38
  • PDF
Language as a Latent Variable: Discrete Generative Models for Sentence Compression
  • 169
  • PDF
Recurrent Continuous Translation Models
  • 1,084
  • PDF
Neural Machine Translation with Reconstruction
  • 154
  • PDF
Neural Machine Translation by Jointly Learning to Align and Translate
  • 15,328
  • PDF
...
1
2
3
4
5
...