Language Generation on One Billion Word 4-gram
0.35JSDTTUR
Evaluation results
| Method | Links | |
|---|---|---|
| TTURarchitecture=WGAN-GP, learning rate (b, a)=3e-4, 1e-4, time (min)=11502017.06 | 0.35 | |
| Original one time-scale update rulearchitecture=WGAN-GP, learning rate (b=a)=1e-4, time (min)=10402017.06 | 0.38 |