SOTAVerified|Agents Browse Leaderboard About

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.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–3 of 3 papers

Title	Date	Tasks	Status	Hype
Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations	Nov 1, 2021	Emotion RecognitionEmpathetic Response Generation	—Unverified	0
Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes	Sep 18, 2021	Dialogue GenerationEmotion Recognition	CodeCode Available	1
Recognizing Emotion Cause in Conversations	Dec 22, 2020	Causal Emotion EntailmentEmotion Cause Extraction	CodeCode Available	1

Show:10 25 50

All datasets EmoCause RECCON

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Human	Top-1 Recall	41.3	—	Unverified
2	GEE	Top-1 Recall	17.3	—	Unverified
3	BERT-Attention	Top-1 Recall	13.8	—	Unverified
4	EmpDG	Top-1 Recall	13.4	—	Unverified
5	RAKE	Top-1 Recall	12.7	—	Unverified
6	Random	Top-1 Recall	10.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SpanBERT	F1	75.71	—	Unverified
2	RoBERTa Base	F1	75.45	—	Unverified