Emotion Recognition In Conversation On Emowoz
Metrics
Macro F1
Macro F1 (w/o Neutral)
Weighted F1
Weighted F1 (w/o Neutral)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Macro F1 | Macro F1 (w/o Neutral) | Weighted F1 | Weighted F1 (w/o Neutral) |
|---|---|---|---|---|
| emowoz-a-large-scale-corpus-and-labelling | 46.33 | 40.14 | 80.76 | 74.56 |
| context-dependent-embedding-utterance | 65.33 | - | - | - |
| emowoz-a-large-scale-corpus-and-labelling | 57.10 | 52.15 | 83.41 | 75.50 |
| emowoz-a-large-scale-corpus-and-labelling | 59.79 | 54.30 | 88.33 | 79.67 |
| emowoz-a-large-scale-corpus-and-labelling | 61.12 | 56.34 | 85.94 | 77.09 |
| emowoz-a-large-scale-corpus-and-labelling | 55.80 | 50.14 | 84.83 | 73.55 |