Dialogue Evaluation on USR-TopicalChat (test)
0.48Pearson Correlation (r)RADE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RADEtrained_on_dataset=false2023.09 | 0.48 | 0.466 | |
| USRtrained_on_dataset=false2023.09 | 0.412 | 0.423 | |
| METEORtrained_on_dataset=false2023.09 | 0.336 | 0.391 | |
| USL-Htrained_on_dataset=false2023.09 | 0.322 | 0.34 | |
| BERTScoretrained_on_dataset=false2023.09 | 0.298 | 0.325 | |
| BLEURTtrained_on_dataset=false2023.09 | 0.216 | 0.261 | |
| GRADEtrained_on_dataset=false2023.09 | 0.2 | 0.217 |