Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations

Open paper
Benchmark Model Rank Results
emotion-recognition-in-conversation-on-4SACL-LSTM (one seed)#4Weighted-F1: 40.47Micro-F1: 43.19
emotion-recognition-in-conversation-on-4SACL-LSTM#8Weighted-F1: 39.65Micro-F1: 42.21
emotion-recognition-in-conversation-on-7SACL-LSTM#7Weighted F1: 80.74Accuracy: 80.70
emotion-recognition-in-conversation-on-cmu-2SACL-LSTM#7Weighted F1: 25.95Accuracy: 38.60
emotion-recognition-in-conversation-on-iemocapSACL-LSTM (one seed)#14Weighted-F1: 69.70Accuracy: 69.62
emotion-recognition-in-conversation-on-iemocapSACL-LSTM#17Weighted-F1: 69.22Accuracy: 69.08
emotion-recognition-in-conversation-on-meldSACL-LSTM (one seed)#8Weighted-F1: 66.86Accuracy: 67.89
emotion-recognition-in-conversation-on-meldSACL-LSTM#16Weighted-F1: 66.45Accuracy: 67.51

Rank counts only results with a code link.