Adversarially-Trained Normalized Noisy-Feature Auto-Encoder for Text Generation

arXiv: Computation and Language, Volume abs/1811.04201, 2018.

Cited by: 0|Bibtex|Views106
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

This article proposes Adversarially-Trained Normalized Noisy-Feature Auto-Encoder (ATNNFAE) for byte-level text generation. An ATNNFAE consists of an auto-encoder where the internal code is normalized on the unit sphere and corrupted by additive noise. Simultaneously, a replica of the decoder (sharing the same parameters as the AE decoder...More

Code:

Data:

Your rating :
0

 

Tags
Comments