Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation

Authors

  • Shuai Lin Shenzhen Campus of Sun Yat-sen University
  • Pan Zhou Salesforce Research
  • Xiaodan Liang Shenzhen Campus of Sun Yat-sen University DarkMatter AI Inc.
  • Jianheng Tang Shenzhen Campus of Sun Yat-sen University
  • Ruihui Zhao Tencent Jarvis Lab
  • Ziliang Chen Shenzhen Campus of Sun Yat-sen University
  • Liang Lin Shenzhen Campus of Sun Yat-sen University DarkMatter AI Inc.

Keywords:

Conversational AI/Dialog Systems

Abstract

Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledge-grounded dialogue systems often require a large number of dialogue instances to learn as they fail to capture the correlations between different diseases and neglect the diagnostic experience shared among them. To address this issue, we propose a more natural and practical paradigm, i.e., low-resource medical dialogue generation, which can transfer the diagnostic experience from source diseases to target ones with a handful of data for adaptation. It is capitalized on a commonsense knowledge graph to characterize the prior disease-symptom relations. Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues. More importantly, by dynamically evolving disease-symptom graphs, GEML also well addresses the real-world challenges that the disease-symptom correlations of each disease may vary or evolve along with more diagnostic cases. Extensive experiment results on the CMDD dataset and our newly-collected Chunyu dataset testify the superiority of our approach over state-of-the-art approaches. Besides, our GEML can generate an enriched dialogue-sensitive knowledge graph in an online manner, which could benefit other tasks grounded on knowledge graph.

Downloads

Published

2021-05-18

How to Cite

Lin, S., Zhou, P., Liang, X., Tang, J., Zhao, R., Chen, Z., & Lin, L. (2021). Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13362-13370. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17577

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing II