Text Generation On Chinese Poems
평가 지표
BLEU-2
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | BLEU-2 | Paper Title | Repository |
|---|---|---|---|
| LeakGAN | 0.456 | Long Text Generation via Adversarial Training with Leaked Information | |
| RankGAN | 0.812 | Adversarial Ranking for Language Generation | |
| SeqGAN | 0.738 | SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient |
0 of 3 row(s) selected.