A Conversation is Worth A Thousand Recommendations: A Survey of Holistic Conversational Recommender Systems

TL;DR

This survey reviews holistic conversational recommender systems that utilize real-world conversational data, highlighting their components, datasets, evaluation methods, challenges, and future directions.

Contribution

It provides a comprehensive structured overview of holistic CRS approaches, analyzing their components, datasets, evaluation methods, and identifying current challenges and future trends.

Findings

Holistic CRS incorporate language models, external knowledge, and guidance.

Real-world conversational data is crucial for effective CRS.

Current challenges include data collection, evaluation, and handling unexpected conversation turns.

Abstract

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.