DeepAI AI Chat
Log In Sign Up

Attention over Parameters for Dialogue Systems

by   Andrea Madotto, et al.
The Hong Kong University of Science and Technology

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.


page 1

page 2

page 3

page 4


BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets

To build open-domain chatbots that are able to use diverse communicative...

Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation

End-to-end generation-based approaches have been investigated and applie...

A Framework for Building Closed-Domain Chat Dialogue Systems

This paper presents PyChat, a framework for developing closed-domain cha...

DialogZoo: Large-Scale Dialog-Oriented Task Learning

Building unified conversational agents has been a long-standing goal of ...

Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues

Task-oriented dialogue systems are designed to achieve specific goals wh...