Noisy Parallel Approximate Decoding for Conditional Recurrent Language Model

Explore this paper's citation graph

Summary

A novel decoding strategy motivated by an earlier observation that nonlinear hidden layers of a deep neural network stretch the data manifold is proposed, which is embarrassingly parallelizable without any communication overhead, while improving an existing decoding algorithm.

Type
preprint
Published
2016-05-12
Cited by
68
References
32
Access
Open access

Keywords

Decoding methods, Computer science, Language model, Artificial intelligence, Natural language processing

References

Cited by

Related papers