Attention over Parameters for Dialogue Systems

Abstract

Dialogue systems require a great deal of different but complementary expertise to assist, inform, and entertain humans. For example, different domains (e.g., restaurant reservation, train ticket booking) of goal-oriented dialogue systems can be viewed as different skills, and so does ordinary chatting abilities of chit-chat dialogue systems. In this paper, we propose to learn a dialogue system that independently parameterizes different dialogue skills, and learns to select and combine each of them through Attention over Parameters (AoP). The experimental results show that this approach achieves competitive performance on a combined dataset of MultiWOZ, In-Car Assistant, and Persona-Chat. Finally, we demonstrate that each dialogue skill is effectively learned and can be combined with other skills to produce selective responses.

NeurIPS Conversational AI Workshops (Best Paper Award)

References in corpus (7)

• Natural Language Processing (almost) from Scratch
• An Overview of Multi-Task Learning in Deep Neural Networks
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• One Model To Learn Them All
• Nonlinear Models Using Dirichlet Process Mixtures
• Generative Deep Neural Networks for Dialogue: A Short Review
• Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

Cited by in corpus (2)

• MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
• Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI