CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts

Authors

  • Peixiang Zhong Alibaba-NTU Singapore Joint Research Institute, Nanyang Technological University (NTU), Singapore Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly, NTU, Singapore
  • Di Wang Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly, NTU, Singapore
  • Pengfei Li School of Electrical and Electronic Engineering, NTU, Singapore
  • Chen Zhang Alibaba Group, China
  • Hao Wang Alibaba Group, China
  • Chunyan Miao Alibaba-NTU Singapore Joint Research Institute, Nanyang Technological University (NTU), Singapore Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly, NTU, Singapore

DOI:

https://doi.org/10.1609/aaai.v35i16.17713

Keywords:

Conversational AI/Dialog Systems

Abstract

Rationality and emotion are two fundamental elements of humans. Endowing agents with rationality and emotion has been one of the major milestones in AI. However, in the field of conversational AI, most existing models only specialize in one aspect and neglect the other, which often leads to dull or unrelated responses. In this paper, we hypothesize that combining rationality and emotion into conversational agents can improve response quality. To test the hypothesis, we focus on one fundamental aspect of rationality, i.e., commonsense, and propose CARE, a novel model for commonsense-aware emotional response generation. Specifically, we first propose a framework to learn and construct commonsense-aware emotional latent concepts of the response given an input message and a desired emotion. We then propose three methods to collaboratively incorporate the latent concepts into response generation. Experimental results on two large-scale datasets support our hypothesis and show that our model can produce more accurate and commonsense-aware emotional responses and achieve better human ratings than state-of-the-art models that only specialize in one aspect.

Downloads

Published

2021-05-18

How to Cite

Zhong, P., Wang, D., Li, P., Zhang, C., Wang, H., & Miao, C. (2021). CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16), 14577-14585. https://doi.org/10.1609/aaai.v35i16.17713

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing III