Modeling Intention, Emotion and External World in Dialogue Systems

TL;DR

This paper introduces RAIN, a novel network that jointly models intention and emotion interactions in dialogue systems, leading to improved understanding of human activities.

Contribution

The paper proposes a new RelAtion Interaction Network (RAIN) that explicitly captures mutual relationships between intention and emotion in dialogue modeling.

Findings

RAIN outperforms BERT-style baselines on the dataset.

Mutual interaction between intention and emotion is crucial for accurate modeling.

Qualitative analysis confirms the importance of intention-emotion interaction.

Abstract

Intention, emotion and action are important elements in human activities. Modeling the interaction process between individuals by analyzing the relationships between these elements is a challenging task. However, previous work mainly focused on modeling intention and emotion independently, and neglected of exploring the mutual relationships between intention and emotion. In this paper, we propose a RelAtion Interaction Network (RAIN), consisting of Intention Relation Module and Emotion Relation Module, to jointly model mutual relationships and explicitly integrate historical intention information. The experiments on the dataset show that our model can take full advantage of the intention, emotion and action between individuals and achieve a remarkable improvement over BERT-style baselines. Qualitative analysis verifies the importance of the mutual interaction between the intention and emotion.