Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals

Abstract

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/.

Accepted by SIGIR 2021

References in corpus (4)

• Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval
• Deep Recurrent Quantization for Generating Sequential Binary Codes
• Towards Deep Conversational Recommendations
• Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems

Cited by in corpus (5)

• Learning Implicit User Profiles for Personalized Retrieval-Based Chatbot
• Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling
• Improving Proactive Dialog Agents Using Socially-Aware Reinforcement Learning
• Sensible Agent: A Framework for Unobtrusive Interaction with Proactive AR Agents
• Bridging the Gap: From Ad-hoc to Proactive Search in Conversations