CNN-VAE

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Adversarial3 results

Text GenerationonYahoo Questions
KL· 2017-02-27
10
SOTA
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions arXiv:1702.08139
Text GenerationonYahoo Questions
NLL· 2017-02-27
332.1
SOTA
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions arXiv:1702.08139
Text GenerationonYahoo Questions
Perplexity· 2017-02-27
63.9
best: 59.7 (Aggressive VAE)
SOTA
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions arXiv:1702.08139