MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System

Rhys Compton, Ilya Valmianski, Li Deng, Costa Huang, Namit Katariya, Xavier Amatriain, Anitha Kannan

Abstract: We present MEDCOD, a Medically-Accurate, Emotive, Diverse, and Controllable Dialog system with a unique approach to the natural language generator module. MEDCOD has been developed and evaluated specifically for the history taking task. It integrates the advantage of a traditional modular-design approach for incorporating (medical) domain knowledge with modern deep learning to generate flexible, human-like natural language expressions. Two key aspects of the human-like character in the natural language output of MEDCOD are described in detail. First, the generated sentences are emotive and empathetic, similar to how a doctor would communicate to the patient. Second, the generated sentence structures and phrasings are varied and diverse, while maintaining medical consistency with the desired medical concept produced by the dialogue manager module of MEDCOD. Experimental results demonstrate the effectiveness of our approach in the development of a human-like medical dialogue system. Relevant code is available at https://github.com/curai/curai-research/tree/main/MEDCOD