Emotion Recognition on EMO
90.6F1 WeightedKEN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| KENBackbone=BLOOM1B7, Trainable params=531M, Reset params (%)=69.172024.02 | 90.6 | — | |
| KENBackbone=BLOOM1B7, Trainable params=664M, Reset params (%)=61.462024.02 | 90.1 | — | |
| KENBackbone=Ernie, Trainable params=69M, Reset params (%)=37.052024.02 | 89.1 | — | |
| KENBackbone=DistilBERT, Trainable params=47M, Reset params (%)=28.922024.02 | 88.8 | — | |
| KENBackbone=Ernie, Trainable params=75M, Reset params (%)=31.82024.02 | 88.7 | — | |
| KENBackbone=DistilBERT, Trainable params=51M, Reset params (%)=23.452024.02 | 88.2 | — | |
| KENBackbone=Ernie, Trainable params=80M, Reset params (%)=26.552024.02 | 88.1 | — | |
| KENBackbone=DistilBERT, Trainable params=44M, Reset params (%)=34.392024.02 | 88.1 | — | |
| KENBackbone=BLOOM1B7, Trainable params=442M, Reset params (%)=74.312024.02 | 88 | — | |
| KENBackbone=DeBERTa, Trainable params=92M, Reset params (%)=33.862024.02 | 87.9 | — | |
| KENBackbone=Bert, Trainable params=80M, Reset params (%)=26.552024.02 | 87.9 | — | |
| KENBackbone=Bert, Trainable params=75M, Reset params (%)=31.82024.02 | 87.4 | — | |
| KENBackbone=DeBERTa, Trainable params=99M, Reset params (%)=28.352024.02 | 87.3 | — | |
| KENBackbone=DeBERTa, Trainable params=107M, Reset params (%)=22.842024.02 | 87.1 | — | |
| KENBackbone=Electra, Trainable params=12M, Reset params (%)=64.752024.02 | 86 | — | |
| KENBackbone=Electra, Trainable params=14M, Reset params (%)=55.942024.02 | 85.6 | — | |
| KENBackbone=Electra, Trainable params=8.9M, Reset params (%)=75.562024.02 | 84.3 | — | |
| KENBackbone=Bert, Trainable params=69M, Reset params (%)=37.052024.02 | 84.2 | — | |
| KENBackbone=BLOOM560M, Trainable params=429M, Reset params (%)=23.262024.02 | 84 | — | |
| KENBackbone=BLOOM560M, Trainable params=420M, Reset params (%)=24.82024.02 | 83 | — | |
| KENBackbone=BLOOM560M, Trainable params=411M, Reset params (%)=26.342024.02 | 81.4 | — | |
| FLOPBackbone=BLOOM1B7, Trainable params=1.1B2024.02 | — | 0.84 | |
| FLOPBackbone=BLOOM560k, Trainable params=408M2024.02 | — | 0.84 | |
| FLOPBackbone=DeBERTa, Trainable params=88M2024.02 | — | 0.831 | |
| FLOPBackbone=Bert, Trainable params=66M2024.02 | — | 0.833 | |
| FLOPBackbone=Ernie, Trainable params=67M2024.02 | — | 0.838 | |
| FLOPBackbone=DistilBERT, Trainable params=45M2024.02 | — | 0.832 | |
| FLOPBackbone=Electra, Trainable params=28M2024.02 | — | 0.831 | |
| KENBackbone=BLOOM1B7, Trainable params=531M2024.02 | — | 0.906 | |
| KENBackbone=BLOOM560k, Trainable params=404M2024.02 | — | 0.855 | |
| KENBackbone=DeBERTa, Trainable params=84M2024.02 | — | 0.889 | |
| KENBackbone=Bert, Trainable params=57M2024.02 | — | 0.86 | |
| KENBackbone=Ernie, Trainable params=57M2024.02 | — | 0.883 | |
| KENBackbone=DistilBERT, Trainable params=40M2024.02 | — | 0.882 | |
| KENBackbone=Electra, Trainable params=14M2024.02 | — | 0.856 |