Knowledge Bridging for Empathetic Dialogue Generation


  • Qintong Li Shandong University The University of Hong Kong
  • Piji Li Tencent AI Lab
  • Zhaochun Ren Shandong University
  • Pengjie Ren Shandong University
  • Zhumin Chen Shandong University



Speech & Natural Language Processing (SNLP)


Lack of external knowledge makes empathetic dialogue systems difficult to perceive implicit emotions and learn emotional interactions from limited dialogue history. To address the above problems, we propose to leverage external knowledge, including commonsense knowledge and emotional lexical knowledge, to explicitly understand and express emotions in empathetic dialogue generation. We first enrich the dialogue history by jointly interacting with external knowledge and construct an emotional context graph. Then we learn emotional context representations from the knowledge-enriched emotional context graph and distill emotional signals, which are the prerequisites to predicate emotions expressed in responses. Finally, to generate the empathetic response, we propose an emotional cross-attention mechanism to learn the emotional dependencies from the emotional context graph. Extensive experiments conducted on a benchmark dataset verify the effectiveness of the proposed method. In addition, we find the performance of our method can be further improved by integrating with a pre-trained model that works orthogonally.




How to Cite

Li, Q., Li, P., Ren, Z., Ren, P., & Chen, Z. (2022). Knowledge Bridging for Empathetic Dialogue Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 10993-11001.



AAAI Technical Track on Speech and Natural Language Processing