Modeling Intention, Emotion and External World in Dialogue Systems
This addresses the challenge of better simulating human-like interactions in dialogue systems, though it appears incremental by focusing on integrating historical intention information.
The paper tackled the problem of modeling the mutual relationships between intention and emotion in dialogue systems, which previous work had neglected, and achieved a remarkable improvement over BERT-style baselines on a dataset.
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.