Attention over Parameters for Dialogue Systems

TL;DR

This paper introduces an Attention over Parameters (AoP) method that independently models and combines various dialogue skills, improving performance across multiple dialogue datasets.

Contribution

It proposes a novel AoP approach to independently parameterize and dynamically select dialogue skills, enhancing multi-domain and multi-task dialogue systems.

Findings

Achieves competitive performance on MultiWOZ, In-Car Assistant, and Persona-Chat datasets.

Effectively learns and combines individual dialogue skills.

Demonstrates skill-specific responses and flexible skill integration.

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.