Story generation on ROC (dev)
28.1BLEU-1KID
Evaluation results
| Method | Links | ||
|---|---|---|---|
| KIDBackbone=GPT2-medium, Parameters=345M, Evaluation Protocol=fine-tuned, Decoding Strategy=KID2022.04 | 28.1 | 21.2 | |
| KIDBackbone=BART-large, Parameters=406M, Evaluation Protocol=fine-tuned, Decoding Strategy=KID2022.04 | 26.5 | 21.3 | |
| GPT2-mediumBackbone=GPT2-medium, Parameters=345M, Evaluation Protocol=fine-tuned, Decoding Strategy=Beam2022.04 | 26.4 | 20.6 | |
| Knowledge-enhanced GPT2Role=Published SotA2022.04 | 26.3 | 20.8 | |
| GPT2-mediumBackbone=GPT2-medium, Parameters=345M, Evaluation Protocol=fine-tuned, Decoding Strategy=Sampling2022.04 | 26 | 20 | |
| BART-largeBackbone=BART-large, Parameters=406M, Evaluation Protocol=fine-tuned, Decoding Strategy=Sampling2022.04 | 24.4 | 20.9 | |
| BART-largeBackbone=BART-large, Parameters=406M, Evaluation Protocol=fine-tuned, Decoding Strategy=Beam2022.04 | 22.3 | 20.2 | |
| BART-largeBackbone=BART-large, Parameters=406M, Evaluation Protocol=zero-shot2022.04 | 12.5 | 16.7 | |
| GPT2-mediumBackbone=GPT2-medium, Parameters=345M, Evaluation Protocol=zero-shot2022.04 | 12 | 13.9 |