Graph-Grounded Goal Planning for Conversational Recommendation

Conversational recommendation casts the recommendation problem as a dialog-based interactive task, which could acquire user interest more efficiently and effectively by allowing users to express what they like. In this work, we move a step towards a new conversational recommendation task that is more suitable for real-world applications. In this task, the recommender will proactively and naturally lead a dialog from non-recommendation content (i.e., chitchat or question answering) to approach an item being of interest to users, and allow users to ask questions about the item for better support of user decisions. The challenge of this task lies in how to effectively control the dialog flow to complete the recommendation while appropriately responding to user utterances. To address this challenge, we first construct a Chinese recommendation dialog dataset with 10k dialogs and 156k utterances at Baidu ( DuRecDial ). We then propose a two-stage Multi-Goal driven Conversation Generation framework ( MGCG ) with a graph-grounded goal planning module and a goal-guided responding module. The goal planning module leverages the information of global graph structure information and local goal-sequence information to effectively control the dialog flow step by step. The goal-guided responding module can produce an in-depth dialog about each goal by fully exploiting hierarchical goal information for response retrieval or generation. Results on DuRecDial demonstrate that compared with the state of the art models, MGCG can lead the dialog more proactively and naturally, and complete the recommendation task more effectively, confirming the benefits of hierarchical goal information to conversational recommendation.