A Flexible Schema-Guided Dialogue Management Framework: From Friendly Peer to Virtual Standardized Cancer Patient

TL;DR

This paper presents a flexible, schema-guided dialogue management framework for creating virtual standardized patients, exemplified by SOPHIE, a cancer patient simulator that outperforms neural models in realism and role consistency.

Contribution

It introduces a general-purpose schema-guided framework for complex medical dialogue management and demonstrates its effectiveness through the development of SOPHIE, a virtual cancer patient.

Findings

SOPHIE produces natural and emotionally appropriate responses.

The schema-guided approach outperforms neural models in realism.

Participants rated SOPHIE highly for role consistency.

Abstract

A schema-guided approach to dialogue management has been shown in recent work to be effective in creating robust customizable virtual agents capable of acting as friendly peers or task assistants. However, successful applications of these methods in open-ended, mixed-initiative domains remain elusive -- particularly within medical domains such as virtual standardized patients, where such complex interactions are commonplace -- and require more extensive and flexible dialogue management capabilities than previous systems provide. In this paper, we describe a general-purpose schema-guided dialogue management framework used to develop SOPHIE, a virtual standardized cancer patient that allows a doctor to conveniently practice for interactions with patients. We conduct a crowdsourced evaluation of conversations between medical students and SOPHIE. Our agent is judged to produce responses that are natural, emotionally appropriate, and consistent with her role as a cancer patient. Furthermore, it significantly outperforms an end-to-end neural model fine-tuned on a human standardized patient corpus, attesting to the advantages of a schema-guided approach.