Question Answering on MOCHA (test)
0.741Pearson's rMARS (default)
Evaluation Results
| Method | Links | |
|---|---|---|
| MARS (default)NLG System=MHPG2021.08 | 0.741 | |
| MARS w/o. self-plan.NLG System=MHPG2021.08 | 0.709 | |
| MARS (default)NLG System=Back-Tran2021.08 | 0.644 | |
| MARS w/o. self-plan.NLG System=Back-Tran2021.08 | 0.631 | |
| Sentence Mover's SimilarityNLG System=MHPG2021.08 | 0.61 | |
| MoverScoreNLG System=MHPG2021.08 | 0.592 | |
| Naive (MLM)NLG System=MHPG2021.08 | 0.54 | |
| MoverScoreNLG System=GPT-22021.08 | 0.535 | |
| MARS (default)NLG System=GPT-22021.08 | 0.526 | |
| Sentence Mover's SimilarityNLG System=GPT-22021.08 | 0.51 | |
| MARS w/o. self-plan.NLG System=GPT-22021.08 | 0.477 | |
| ROUGE-LNLG System=GPT-22021.08 | 0.468 | |
| METEORNLG System=GPT-22021.08 | 0.466 | |
| BERTScoreNLG System=MHPG2021.08 | 0.458 | |
| BERTScoreNLG System=GPT-22021.08 | 0.444 | |
| Naive (MLM)NLG System=GPT-22021.08 | 0.443 | |
| METEORNLG System=MHPG2021.08 | 0.409 | |
| BLEU-1NLG System=GPT-22021.08 | 0.328 | |
| BLEU-1NLG System=MHPG2021.08 | 0.318 | |
| Naive (MLM)NLG System=Back-Tran2021.08 | 0.307 | |
| MARS w/o. contextNLG System=MHPG2021.08 | 0.303 | |
| MARS w/o. bothNLG System=MHPG2021.08 | 0.299 | |
| BERTScoreNLG System=Back-Tran2021.08 | 0.274 | |
| ROUGE-LNLG System=MHPG2021.08 | 0.247 | |
| MARS w/o. contextNLG System=Back-Tran2021.08 | 0.222 | |
| MoverScoreNLG System=Back-Tran2021.08 | 0.19 | |
| METEORNLG System=Back-Tran2021.08 | 0.179 | |
| Sentence Mover's SimilarityNLG System=Back-Tran2021.08 | 0.166 | |
| MARS w/o. contextNLG System=GPT-22021.08 | 0.134 | |
| MARS w/o. bothNLG System=Back-Tran2021.08 | 0.121 | |
| BLEU-1NLG System=Back-Tran2021.08 | 0.061 | |
| ROUGE-LNLG System=Back-Tran2021.08 | 0.056 | |
| PerplexityNLG System=GPT-22021.08 | 0.014 | |
| PerplexityNLG System=Back-Tran2021.08 | -0.051 | |
| MARS w/o. bothNLG System=GPT-22021.08 | -0.092 | |
| PerplexityNLG System=MHPG2021.08 | -0.128 |