Meta-CRS: A Dynamic Meta-Learning Approach for Effective Conversational Recommender System

Citations Over TimeTop 10% of 2023 papers

Abstract

Conversational recommender system (CRS) enhances the recommender system by acquiring the latest user preference through dialogues, where an agent needs to decide “whether to ask or recommend”, “which attributes to ask”, and “which items to recommend” in each round. To explore these questions, reinforcement learning is adopted in most CRS frameworks. However, existing studies somewhat ignore to consider the connection between the previous rounds and the current round of the conversation, which might lead to the lack of prior knowledge and inaccurate decisions. In this view, we propose to facilitate the connections between different rounds of conversations in a dialogue session through deep transformer-based multi-channel meta-reinforcement learning, so that the CRS agent can decide each action/decision based on previous states, actions, and their rewards. Besides, to better utilize a user’s historical preferences, we propose a more dynamic and personalized graph structure to support the conversation module and the recommendation module. Experiment results on five real-world datasets and an online evaluation with real users in an industrial environment validate the improvement of our method over the state-of-the-art approaches and the effectiveness of our designs.

Related Papers

• → The effect of familiarity of conversation partners on conversation turns contributed by augmented and typical speakers(2013)9 cited
• → Support for Content Creation Using Conversation Quanta(2006)2 cited
• Conversation and the Relevance and Turn Transition in Conversation(2004)
• A Preliminary Study on Conversation Repair(2012)
• 深まりのある意見交換は接觸場面において どのように達成されるか - 對話／共話との關連から -(2017)