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

TL;DR

This paper introduces PAGE, a position-aware graph model that captures causal relations in conversations to improve emotion cause entailment detection, achieving state-of-the-art results.

Contribution

The paper proposes a novel position-aware graph encoding method that models causal relations among utterances, addressing limitations of previous position encoding strategies.

Findings

Achieves state-of-the-art performance on two test sets

Effectively models causal relations in conversations

Demonstrates the importance of position-aware encoding

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 Github: https://github.com/XiaojieGu/PAGE.