Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Components
This review synthesizes existing knowledge to guide the development of conversational search systems, addressing a gap between theory and practice for researchers and engineers, but it is incremental as it consolidates prior work without new empirical results.
The authors conducted a systematic literature review to understand the engineering of conversational search systems, identifying application scenarios, architectures, and functional components, and presented a layered framework while discussing the impact of large language models.
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.