Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Components
Phillip Schneider, Wessel Poelman, Michael Rovatsos, Florian Matthes
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.- Anthology ID:
- 2024.nlp4convai-1.5
- Original:
- 2024.nlp4convai-1.5v1
- Version 2:
- 2024.nlp4convai-1.5v2
- Volume:
- Proceedings of the 6th Workshop on NLP for Conversational AI (NLP4ConvAI 2024)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Elnaz Nouri, Abhinav Rastogi, Georgios Spithourakis, Bing Liu, Yun-Nung Chen, Yu Li, Alon Albalak, Hiromi Wakaki, Alexandros Papangelis
- Venues:
- NLP4ConvAI | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 73–88
- Language:
- URL:
- https://aclanthology.org/2024.nlp4convai-1.5
- DOI:
- Cite (ACL):
- Phillip Schneider, Wessel Poelman, Michael Rovatsos, and Florian Matthes. 2024. Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Components. In Proceedings of the 6th Workshop on NLP for Conversational AI (NLP4ConvAI 2024), pages 73–88, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Components (Schneider et al., NLP4ConvAI-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2024.nlp4convai-1.5.pdf