A Conversation is Worth A Thousand Recommendations: A Survey of Holistic Conversational Recommender Systems
This survey highlights the need for more realistic conversational recommender systems, which could improve user experience in applications like e-commerce or customer service, but it is incremental as it reviews existing work rather than proposing new methods.
The paper addresses the problem that most conversational recommender systems (CRS) use simulated interactions, which do not generalize to real-world conversations with unexpected turns or imperfect understanding, by surveying holistic CRS methods trained on real-world conversational data. It provides a structured summary of these approaches, analyzing their components, datasets, and evaluation methods, and discusses current challenges and future trends.
Conversational recommender systems (CRS) generate recommendations through an interactive process. However, not all CRS approaches use human conversations as their source of interaction data; the majority of prior CRS work simulates interactions by exchanging entity-level information. As a result, claims of prior CRS work do not generalise to real-world settings where conversations take unexpected turns, or where conversational and intent understanding is not perfect. To tackle this challenge, the research community has started to examine holistic CRS, which are trained using conversational data collected from real-world scenarios. Despite their emergence, such holistic approaches are under-explored. We present a comprehensive survey of holistic CRS methods by summarizing the literature in a structured manner. Our survey recognises holistic CRS approaches as having three components: 1) a backbone language model, the optional use of 2) external knowledge, and/or 3) external guidance. We also give a detailed analysis of CRS datasets and evaluation methods in real application scenarios. We offer our insight as to the current challenges of holistic CRS and possible future trends.