Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals
This work addresses the challenge of building more engaging and goal-oriented dialogue systems for applications like recommendation, though it is incremental in its approach.
The paper tackles the problem of enabling chatbots to proactively lead conversations by proposing a multi-task learning framework that explicitly models knowledge prediction and goal selection for retrieval-based dialogue systems, achieving significant improvements in response selection.
A proactive dialogue system has the ability to proactively lead the conversation. Different from the general chatbots which only react to the user, proactive dialogue systems can be used to achieve some goals, e.g., to recommend some items to the user. Background knowledge is essential to enable smooth and natural transitions in dialogue. In this paper, we propose a new multi-task learning framework for retrieval-based knowledge-grounded proactive dialogue. To determine the relevant knowledge to be used, we frame knowledge prediction as a complementary task and use explicit signals to supervise its learning. The final response is selected according to the predicted knowledge, the goal to achieve, and the context. Experimental results show that explicit modeling of knowledge prediction and goal selection can greatly improve the final response selection. Our code is available at https://github.com/DaoD/KPN/.