PAGE: A Position-Aware Graph-Based Model for Emotion Cause Entailment in Conversation
TL
TL;DR
A novel position-aware graph is devised to encode the entire conversation, fully modeling causal relations among utterances, and consistently achieves state-of-the-art performance on two challenging test sets, proving the effectiveness of the model.
Abstract
Conversational Causal Emotion Entailment (C2E2) is a task that aims at recognizing the causes corresponding to a target emotion in a conversation. The order of utterances in the conversation affects the causal inference. However, most current position encoding strategies ignore the order relation among utterances and speakers. To address the issue, we devise a novel position-aware graph to encode the entire conversation, fully modeling causal relations among utterances. The comprehensive experiments show that our method consistently achieves state-of-the-art performance on two challenging test sets, proving the effectiveness of our model. Our source code is available on Github1.
References27 items
1
Emotionflow: Capture the Dialogue Level Emotion Transitions
2
Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledge
3
Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction
4
Towards Emotional Support Dialog Systems
5