Command Palette
Search for a command to run...
Dialogue Evaluation On Usr Personachat
評価指標
Pearson Correlation
Spearman Correlation
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
| Paper Title | |||
|---|---|---|---|
| USR - DR (x = c) | 0.6087 | 0.4814 | USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation |
| Lin-Reg (all) | 0.5290 | 0.5382 | Proxy Indicators for the Quality of Open-domain Dialogues |
| USR | 0.4115 | 0.4693 | USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation |
| USR - MLM | 0.0788 | 0.0795 | USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation |
| USR - DR (x = f) | -0.0454 | -0.0495 | USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation |
0 of 5 row(s) selected.