Story Generation on ROC Stories (test)
0.476Pearson's rMARS (default)
Evaluation Results
| Method | Links | |
|---|---|---|
| MARS (default)NLG System=Solr2021.08 | 0.476 | |
| Naive (MLM)NLG System=Solr2021.08 | 0.449 | |
| MARS (default)NLG System=Open-NMT2021.08 | 0.397 | |
| MoverScoreNLG System=Open-NMT2021.08 | 0.391 | |
| BERTScoreNLG System=Open-NMT2021.08 | 0.386 | |
| MARS w/o. contextNLG System=Solr2021.08 | 0.36 | |
| MARS w/o. contextNLG System=Open-NMT2021.08 | 0.334 | |
| MARS w/o. self-plan.NLG System=Solr2021.08 | 0.313 | |
| MARS w/o. bothNLG System=Solr2021.08 | 0.276 | |
| BERTScoreNLG System=Solr2021.08 | 0.245 | |
| MARS w/o. self-plan.NLG System=Open-NMT2021.08 | 0.212 | |
| BLEU-1NLG System=Solr2021.08 | 0.198 | |
| Naive (MLM)NLG System=Open-NMT2021.08 | 0.197 | |
| ROUGE-LNLG System=Open-NMT2021.08 | 0.195 | |
| MARS w/o. bothNLG System=Open-NMT2021.08 | 0.183 | |
| MoverScoreNLG System=Solr2021.08 | 0.181 | |
| METEORNLG System=Solr2021.08 | 0.18 | |
| ROUGE-LNLG System=Solr2021.08 | 0.118 | |
| METEORNLG System=Open-NMT2021.08 | 0.116 | |
| BLEU-1NLG System=Open-NMT2021.08 | 0.104 | |
| Sentence Mover's SimilarityNLG System=Solr2021.08 | 0.02 | |
| Sentence Mover's SimilarityNLG System=Open-NMT2021.08 | 0.015 | |
| PerplexityNLG System=Open-NMT2021.08 | -0.073 | |
| PerplexityNLG System=Solr2021.08 | -0.104 |