TSAM: A Two-Stream Attention Model for Causal Emotion Entailment
TL
TL;DR
A Two-Stream Attention Model (TSAM) is proposed to effectively model the speaker’s emotional influences in the conversational history and achieves new State-Of-The-Art (SOTA) performance and outperforms baselines remarkably.
Abstract
Causal Emotion Entailment (CEE) aims to discover the potential causes behind an emotion in a conversational utterance. Previous works formalize CEE as independent utterance pair classification problems, with emotion and speaker information neglected. From a new perspective, this paper considers CEE in a joint framework. We classify multiple utterances synchronously to capture the correlations between utterances in a global view and propose a Two-Stream Attention Model (TSAM) to effectively model the speaker’s emotional influences in the conversational history. Specifically, the TSAM comprises three modules: Emotion Attention Network (EAN), Speaker Attention Network (SAN), and interaction module. The EAN and SAN incorporate emotion and speaker information in parallel, and the subsequent interaction module effectively interchanges relevant information between the EAN and SAN via a mutual BiAffine transformation. Extensive experimental results demonstrate that our model achieves new State-Of-The-Art (SOTA) performance and outperforms baselines remarkably.
References54 items
1
COMMA: Modeling Relationship among Motivations, Emotions and Actions in Language-based Human Activities
2
CauAIN: Causal Aware Interaction Network for Emotion Recognition in Conversations
3
Do You Know My Emotion? Emotion-Aware Strategy Recognition towards a Persuasive Dialogue System
4
Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks
5