Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption
arXiv:2005.11153
Abstract
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.
References in corpus (10)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Playing Atari with Deep Reinforcement Learning
- Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
- Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
- Learning End-to-End Goal-Oriented Dialog
- Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems
- Evaluating Visual Conversational Agents via Cooperative Human-AI Games
- Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
- Domain Adaptive Dialog Generation via Meta Learning