Dialogue State Tracking On Mmconv
Metrics
Categorical Accuracy
Non-Categorical Accuracy
Overall
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Categorical Accuracy | Non-Categorical Accuracy | Overall |
|---|---|---|---|
| pace-unified-multi-modal-dialogue-pre | 92.2 | 43.4 | 39.2 |
| mconv-an-environment-for-multimodal | 91.0 | 23.0 | 18.0 |