Multi-turn Dialog System on Single-turn Data in Medical Domain

TL;DR

This paper explores building a multi-turn medical dialog system using limited verified single-turn FAQ data, addressing data scarcity challenges in the medical domain.

Contribution

It proposes a method to develop multi-turn medical dialog systems leveraging existing single-turn verified FAQ pairs, reducing the need for extensive multi-turn data collection.

Findings

Effective multi-turn dialog system built from single-turn FAQs

Improved performance over baseline models in medical conversations

Demonstrates feasibility of using verified FAQs for complex dialog tasks

Abstract

Recently there has been a huge interest in dialog systems. This interest has also been developed in the field of the medical domain where researchers are focusing on building a dialog system in the medical domain. This research is focused on the multi-turn dialog system trained on the multi-turn dialog data. It is difficult to gather a huge amount of multi-turn conversational data in the medical domain that is verified by professionals and can be trusted. However, there are several frequently asked questions (FAQs) or single-turn QA pairs that have information that is verified by the experts and can be used to build a multi-turn dialog system.