EmoOne-RoBERTa

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio4 results

Emotion RecognitiononDailyDialog
Macro F1· 2022-06-15
55.84
SOTA
The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation arXiv:2206.07359
Emotion RecognitiononEmoryNLP
Weighted-F1· 2022-06-15
38
best: 42.08 (CKERC)
The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation arXiv:2206.07359
Emotion RecognitiononMELD
Weighted-F1· 2022-06-15
66.49
best: 69.9 (ELR-GNN)
The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation arXiv:2206.07359
Emotion RecognitiononDailyDialog
Micro-F1· 2022-06-15
61.67
best: 64.07 (S+PAGE)
The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation arXiv:2206.07359