DeepAI AI Chat
Log In Sign Up

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

by   Rhys Compton, et al.
NYU college

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 approach to incorporate (medical) domain knowledge with modern deep learning techniques to generate flexible, human-like natural language expressions. Two key aspects of MEDCOD's natural language output 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 (provided by the dialogue manager module of MEDCOD). Experimental results demonstrate the effectiveness of our approach in creating a human-like medical dialogue system. Relevant code is available at


Terminology-aware Medical Dialogue Generation

Medical dialogue generation aims to generate responses according to a hi...

Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems

Cross-domain natural language generation (NLG) is still a difficult task...

Controllable Dialogue Simulation with In-Context Learning

Building dialogue systems requires a large corpus of annotated dialogues...

Designing Precise and Robust Dialogue Response Evaluators

Automatic dialogue response evaluator has been proposed as an alternativ...

Learning functional sections in medical conversations: iterative pseudo-labeling and human-in-the-loop approach

Medical conversations between patients and medical professionals have im...

Lessons from Natural Language Inference in the Clinical Domain

State of the art models using deep neural networks have become very good...

Learning Neural Templates for Recommender Dialogue System

Though recent end-to-end neural models have shown promising progress on ...