Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption
This addresses the challenge of few-shot adaptation in medical dialog systems for healthcare applications, representing an incremental improvement over existing methods.
The paper tackled the problem of adapting automatic conversational diagnosis systems to new diseases with few training samples, proposing Prototypical Q Networks (ProtoQN) that significantly outperformed baseline DQN models and achieved state-of-the-art few-shot learning performances.
Spoken dialog systems have seen applications in many domains, including medical for automatic conversational diagnosis. State-of-the-art dialog managers are usually driven by deep reinforcement learning models, such as deep Q networks (DQNs), which learn by interacting with a simulator to explore the entire action space since real conversations are limited. However, the DQN-based automatic diagnosis models do not achieve satisfying performances when adapted to new, unseen diseases with only a few training samples. In this work, we propose the Prototypical Q Networks (ProtoQN) as the dialog manager for the automatic diagnosis systems. The model calculates prototype embeddings with real conversations between doctors and patients, learning from them and simulator-augmented dialogs more efficiently. We create both supervised and few-shot learning tasks with the Muzhi corpus. Experiments showed that the ProtoQN significantly outperformed the baseline DQN model in both supervised and few-shot learning scenarios, and achieves state-of-the-art few-shot learning performances.