Story Generation On Fandom Dev
Metrics
BLEU
Perplexity
ROUGE-1
ROUGE-2
ROUGE-L
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | BLEU | Perplexity | ROUGE-1 | ROUGE-2 | ROUGE-L |
|---|---|---|---|---|---|
| tvrecap-a-dataset-for-generating-stories-with | 28.4 | 17.9 | 63.0 | 32.8 | 61.2 |