| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Slot Filling | MWOZ | Micro F199.28 | 18 | |
| Intent Detection | MWOZ | Accuracy85.02 | 18 | |
| Response Selection | MWOZ 2.1 | Accuracy (1/100)68.5 | 17 | |
| Domain Classification | MWOZ | Accuracy88.16 | 16 | |
| User Satisfaction Estimation | MWOZ | Accuracy58.1 | 14 | |
| User Satisfaction Estimation | MWOZ 5% training size (test) | Precision68.4 | 8 | |
| Dialogue act prediction | MWOZ (Full Data) | Micro-F192 | 7 | |
| Dialogue act prediction | MWOZ (1% Data) | Micro-F187.9 | 6 | |
| Dialogue State Tracking | MWOZ 2.1 (Full Data) | Joint Accuracy50.4 | 6 | |
| Dialogue State Tracking | MWOZ 2.1 (25% Data) | Joint Accuracy45.7 | 6 | |
| Dialogue State Tracking | MWOZ 2.1 (10% Data) | Joint Accuracy40.7 | 6 | |
| Dialogue act prediction | MWOZ 10% Data 2.1 | Micro F191 | 6 | |
| Dialogue act prediction | MWOZ Full Data 2.1 | Micro-F1- | 0 | |
| Dialogue act prediction | MWOZ 2.1 (1% Data) | Micro F1- | 0 | |
| Response Selection | MWOZ | Accuracy (1-to-100)- | 0 |