Semi-Supervised Variational Reasoning for Medical Dialogue Generation

Abstract

Medical dialogue generation aims to provide automatic and accurate responses to assist physicians to obtain diagnosis and treatment suggestions in an efficient manner. In medical dialogues two key characteristics are relevant for response generation: patient states (such as symptoms, medication) and physician actions (such as diagnosis, treatments). In medical scenarios large-scale human annotations are usually not available, due to the high costs and privacy requirements. Hence, current approaches to medical dialogue generation typically do not explicitly account for patient states and physician actions, and focus on implicit representation instead. We propose an end-to-end variational reasoning approach to medical dialogue generation. To be able to deal with a limited amount of labeled data, we introduce both patient state and physician action as latent variables with categorical priors for explicit patient state tracking and physician policy learning, respectively. We propose a variational Bayesian generative approach to approximate posterior distributions over patient states and physician actions. We use an efficient stochastic gradient variational Bayes estimator to optimize the derived evidence lower bound, where a 2-stage collapsed inference method is proposed to reduce the bias during model training. A physician policy network composed of an action-classifier and two reasoning detectors is proposed for augmented reasoning ability. We conduct experiments on three datasets collected from medical platforms. Our experimental results show that the proposed method outperforms state-of-the-art baselines in terms of objective and subjective evaluation metrics. Our experiments also indicate that our proposed semi-supervised reasoning method achieves a comparable performance as state-of-the-art fully supervised learning baselines for physician policy learning.

arXiv commentAccepted by Sigir2021

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• Categorical Reparameterization with Gumbel-Softmax
• KGAT: Knowledge Graph Attention Network for Recommendation
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• A Survey on Dialogue Systems: Recent Advances and New Frontiers
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Relational Graph Attention Networks
• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
• PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation
• Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
• Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation
• Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems
• Conversations with Documents. An Exploration of Document-Centered Assistance
• Summarizing and Exploring Tabular Data in Conversational Search
• An Analysis of Mixed Initiative and Collaboration in Information-Seeking Dialogues
• On the Generation of Medical Dialogues for COVID-19
• A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning
• Rethinking Dialogue State Tracking with Reasoning

Cited by in corpus (5)

• Natural Language Processing for Smart Healthcare
• A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
• Pre-trained Language Models in Biomedical Domain: A Systematic Survey
• Efficient Symptom Inquiring and Diagnosis via Adaptive Alignment of Reinforcement Learning and Classification
• SynDocDis: A Metadata-Driven Framework for Generating Synthetic Physician Discussions Using Large Language Models