Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems
This work addresses the challenge of naturally guiding users to accept designated targets in recommendation dialogues, which is an incremental advancement in a promising but under-explored paradigm.
The paper tackles the problem of target-driven recommendation dialogue systems by proposing a Target-driven Conversation Planning (TCP) framework to plan dialogue actions and topics, leading to significant performance improvements in these systems.
Recommendation dialogue systems aim to build social bonds with users and provide high-quality recommendations. This paper pushes forward towards a promising paradigm called target-driven recommendation dialogue systems, which is highly desired yet under-explored. We focus on how to naturally lead users to accept the designated targets gradually through conversations. To this end, we propose a Target-driven Conversation Planning (TCP) framework to plan a sequence of dialogue actions and topics, driving the system to transit between different conversation stages proactively. We then apply our TCP with planned content to guide dialogue generation. Experimental results show that our conversation planning significantly improves the performance of target-driven recommendation dialogue systems.