MAE (Valence): 0.157MAE (Arousal): 0.161MAE (Expectancy): 0.168MAE (Power): 7.68
Papers with Code · CC BY-SA 4.0
Emotion Recognition in Conversation
Given the transcript of a conversation along with speaker information of each constituent utterance, the ERC task aims to identify the emotion of each utterance from several pre-defined emotions. Formally, given the input sequence of N number of utterances [(u1, p1), (u2, p2), . . . , (uN , pN )], where each utterance ui = [ui,1, ui,2, . . . , ui,T ] consists of T words ui,j and spoken by party pi, the task is to predict the emotion label ei of each utterance ui. .
논문
MAE (Valence): 0.168MAE (Arousal): 0.165MAE (Expectancy): 0.175MAE (Power): 7.9
Weighted-F1: 40.47Micro-F1: 43.19
Weighted-F1: 39.33
Accuracy of Sentiment: 48.62Macro-F1 of Sentiment: 30.33
Accuracy of Sentiment: 48.96Macro-F1 of Sentiment: 45.18
Weighted-F1: 41.68
Weighted-F1: 42.08
Accuracy of Sentiment: 49.65Macro-F1 of Sentiment: 45.40
Weighted-F1: 39.04Micro-F1: 42.58
Accuracy of Sentiment: 48.90Macro-F1 of Sentiment: 34.37
Accuracy of Sentiment: 51.50Macro-F1 of Sentiment: 48.02
Weighted-F1: 38.79Micro-F1: 41.04
Accuracy of Sentiment: 51.24Macro-F1 of Sentiment: 46.96
Weighted-F1: 39.02
Accuracy of Sentiment: 48.09Macro-F1 of Sentiment: 44.60
Weighted-F1: 40.24
Weighted-F1: 40.25Micro-F1: 44.31
Weighted-F1: 39.24
Weighted-F1: 40
MAE (Valence): 0.16MAE (Arousal): 0.16MAE (Expectancy): 0.16MAE (Power): 7.70
Weighted-F1: 41.39
Weighted-F1: 38.88
Accuracy of Sentiment: 49.13Macro-F1 of Sentiment: 37.95
Accuracy of Sentiment: 47.89Macro-F1 of Sentiment: 37.07
Weighted-F1: 39.14
Weighted-F1: 40.94