Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Open-ended text generation evaluation (Discriminator Accuracy) on Stories
Loading...
0.643
Gen. PPL
Gen. PPL
0.61085
0.626925
0.643
0.659075
Feb 2, 2021
Gen. PPL
Zipf Coef.
REP
Distinct-4
Self-BLEU
MAUVE
Updated 4d ago
Evaluation Results
Method
Method
Links
Gen. PPL
Zipf Coef.
REP
Distinct-4
Self-BLEU
MAUVE
Gen. PPL
2021.02
0.643
-
-
-
-
-
Zipf Coef.
2021.02
-
0.643
-
-
-
-
REP
2021.02
-
-
0.25
-
-
-
Distinct-4
2021.02
-
-
-
75
-
-
Self-BLEU
2021.02
-
-
-
-
85.7
-
MAUVE
2021.02
-
-
-
-
-
0.893
Feedback
Search any
task
Search any
task