English

Attention over Parameters for Dialogue Systems

Computation and Language 2020-03-05 v2 Machine Learning

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.

Keywords

Cite

@article{arxiv.2001.01871,
  title  = {Attention over Parameters for Dialogue Systems},
  author = {Andrea Madotto and Zhaojiang Lin and Chien-Sheng Wu and Jamin Shin and Pascale Fung},
  journal= {arXiv preprint arXiv:2001.01871},
  year   = {2020}
}

Comments

NeurIPS Conversational AI Workshops (Best Paper Award)

R2 v1 2026-06-23T13:04:35.672Z