Responsive and Self-Expressive Dialogue Generation

Generic responses frequently generated by neural models are a critical problem for user engagement in dialogue systems. For a more engaging chit-chat experience, we propose a response generation model motivated by the interpersonal process model for intimacy. It generates responsive and self-expressive replies, which are implemented as domain-awareness and sentiment-richness, respectively. Experiments empirically confirmed that our model outperformed the sequence-to-sequence model; 68.1% of our responses were domain-aware with sentiment polarities, which was only 2.7% for responses generated by the sequence-to-sequence model.