Top-1 Recall: 41.3Top-3 Recall: 81.1Top-5 Recall: 95.0
Papers with Code · CC BY-SA 4.0
Recognizing Emotion Cause in Conversations
Given an utterance U, labeled with emotion E, the task is to extract the causal spans S from the conversational history H (including utterance U) that sufficiently represent the causes of emotion E.
논문
Exact Span F1: 34.64F1: 75.71F1(Pos): 60.00F1(Neg): 86.02
Pos. F1: 67.91Neg. F1: 89.55Macro F1: 78.73
Pos. F1: 68.59Neg. F1: 89.65Macro F1: 79.12
Pos. F1: 71.18Neg. F1: 90.35Macro F1: 80.76
Pos. F1: 69.20Neg. F1: 85.90Macro F1: 77.55
Pos. F1: 66.76Neg. F1: 95.74Macro F1: 81.25
Pos. F1: 70.00Neg. F1: 90.48Macro F1: 80.24
Pos. F1: 63.10Neg. F1: 97.69Macro F1: 80.53