A Survey on Conversational Search and Applications in Biomedicine

TL;DR

This survey reviews conversational search systems, focusing on their components, challenges, and applications in biomedicine, aiming to unify knowledge across fields to improve healthcare information retrieval.

Contribution

It provides an integrated overview of ConvSearch systems, emphasizing biomedical applications, and discusses research problems, frameworks, and challenges in this domain.

Findings

Categorized ConvSearch research problems in knowledge bases and NLP

Highlighted the role of action modules like retrieval and QA

Discussed challenges specific to biomedical applications

Abstract

This paper aims to provide a radical rundown on Conversation Search (ConvSearch), an approach to enhance the information retrieval method where users engage in a dialogue for the information-seeking tasks. In this survey, we predominantly focused on the human interactive characteristics of the ConvSearch systems, highlighting the operations of the action modules, likely the Retrieval system, Question-Answering, and Recommender system. We labeled various ConvSearch research problems in knowledge bases, natural language processing, and dialogue management systems along with the action modules. We further categorized the framework to ConvSearch and the application is directed toward biomedical and healthcare fields for the utilization of clinical social technology. Finally, we conclude by talking through the challenges and issues of ConvSearch, particularly in Bio-Medicine. Our main aim is to provide an integrated and unified vision of the ConvSearch components from different fields, which benefit the information-seeking process in healthcare systems.