Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Components

TL;DR

This paper systematically reviews the engineering aspects of conversational search systems, exploring their applications, architectures, and components, and discusses future directions considering recent advances in large language models.

Contribution

It provides a comprehensive layered architecture framework and links theoretical research with practical implementations of conversational search systems.

Findings

Identified key real-world application scenarios

Proposed a layered architecture framework

Discussed the impact of large language models on future research

Abstract

Conversational search systems enable information retrieval via natural language interactions, with the goal of maximizing users' information gain over multiple dialogue turns. The increasing prevalence of conversational interfaces adopting this search paradigm challenges traditional information retrieval approaches, stressing the importance of better understanding the engineering process of developing these systems. We undertook a systematic literature review to investigate the links between theoretical studies and technical implementations of conversational search systems. Our review identifies real-world application scenarios, system architectures, and functional components. We consolidate our results by presenting a layered architecture framework and explaining the core functions of conversational search systems. Furthermore, we reflect on our findings in light of the rapid progress in large language models, discussing their capabilities, limitations, and directions for future research.