Causal Emotion Entailment

9 papers with code • 1 benchmarks • 1 datasets

The Causal Emotion Entailment is a simpler version of the span extraction task. In this task, given a target utterance (U) with emotion E, the goal is to predict which particular utterances in the conversation history H(U) are responsible for the emotion E in the target utterance.


Most implemented papers

Towards Interpretable Mental Health Analysis with Large Language Models

stevekgyang/mentalllama 6 Apr 2023

The latest large language models (LLMs) such as ChatGPT, exhibit strong capabilities in automated mental health analysis.

Recognizing Emotion Cause in Conversations

declare-lab/RECCON 22 Dec 2020

We address the problem of recognizing emotion cause in conversations, define two novel sub-tasks of this problem, and provide a corresponding dialogue-level dataset, along with strong Transformer-based baselines.

A Commonsense Reasoning Framework for Explanatory Emotion Attribution, Generation and Re-classification

alieto/DEGARI 11 Jan 2021

We present DEGARI (Dynamic Emotion Generator And ReclassIfier), an explainable system for emotion attribution and recommendation.

TSAM: A Two-Stream Attention Model for Causal Emotion Entailment

bladedancer957/tsam COLING 2022

Causal Emotion Entailment (CEE) aims to discover the potential causes behind an emotion in a conversational utterance.

Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledge

leqsnan/kec 2 May 2022

Conversational Causal Emotion Entailment aims to detect causal utterances for a non-neutral targeted utterance from a conversation.

Multi-Task Learning Framework for Extracting Emotion Cause Span and Entailment in Conversations

exploration-lab/mutec 7 Nov 2022

Recently there has been active research in extracting the cause of an emotion expressed in text.

Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailment

circle-hit/kbcin 6 Dec 2022

Moreover, social-interaction CSK serves as emotion-level bridge (E-bridge) and action-level bridge (A-bridge) to connect candidate utterances with the target one, which provides explicit causal clues for the Emotional Interaction module and Actional Interaction module to reason the target emotion.

PAGE: A Position-Aware Graph-Based Model for Emotion Cause Entailment in Conversation

xiaojiegu/page 3 Mar 2023

Conversational Causal Emotion Entailment (C2E2) is a task that aims at recognizing the causes corresponding to a target emotion in a conversation.

ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains

hzp3517/ecr-chain 17 May 2024

In this work, inspired by the emotion generation process of "stimulus-appraisal-emotion" in the cognitive appraisal theory, we introduce a step-by-step reasoning method, Emotion-Cause Reasoning Chain (ECR-Chain), to infer the stimulus from the target emotional expressions in conversations.