Attention over Parameters for Dialogue Systems

Andrea Madotto, Zhaojiang Lin, Chien-Sheng Wu, Jamin Shin, Pascale Fung

Keywords: end-to-end dialogue systems, natural language processing

TL;DR: 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).

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 (Budzianowski et al., 2018), In-Car Assistant (Eric et al.,2017), and Persona-Chat (Zhang et al., 2018). Finally, we demonstrate that each dialogue skill is effectively learned and can be combined with other skills to produce selective responses.