Dialogue Evaluation on Chatbot Domain
0.93Correlation ScoreHuman
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| HumanProtocol=Proposed Bayesian Protocol (Algorithm 2)2023.06 | 0.93 | 0 | 0 | 7 | 0.05 | 0.59 | |
| DEBProtocol=Proposed Bayesian Protocol (Algorithm 2)2023.06 | 0.93 | 0 | 0 | 7 | 0.06 | 0.49 | |
| GRADEProtocol=Proposed Bayesian Protocol (Algorithm 2)2023.06 | 0.87 | 0 | 0 | 13 | 0.05 | 0.53 | |
| HOLISTICProtocol=Proposed Bayesian Protocol (Algorithm 2)2023.06 | 0.87 | 0 | 0 | 13 | 0.05 | 0.52 | |
| MAUDEProtocol=Proposed Bayesian Protocol (Algorithm 2)2023.06 | 0.87 | 0 | 0 | 13 | 0.05 | 0.53 | |
| USL-HProtocol=Proposed Bayesian Protocol (Algorithm 2)2023.06 | 0.87 | 0 | 0 | 13 | 0.05 | 0.52 |