A Framework for Building Closed-Domain Chat Dialogue Systems

TL;DR

This paper introduces HRIChat, a framework for creating closed-domain chat dialogue systems that effectively handle domain-specific language and integrate multiple dialogue management strategies, demonstrated through a food chatbot application.

Contribution

The paper presents a novel framework, HRIChat, enabling domain-dependent language understanding and flexible dialogue management for closed-domain chatbots.

Findings

FoodChatbot achieved positive user evaluation results.

HRIChat effectively handles domain-specific utterances.

The framework facilitates integration of different dialogue management methods.

Abstract

This paper presents HRIChat, a framework for developing closed-domain chat dialogue systems. Being able to engage in chat dialogues has been found effective for improving communication between humans and dialogue systems. This paper focuses on closed-domain systems because they would be useful when combined with task-oriented dialogue systems in the same domain. HRIChat enables domain-dependent language understanding so that it can deal well with domain-specific utterances. In addition, HRIChat makes it possible to integrate state transition network-based dialogue management and reaction-based dialogue management. FoodChatbot, which is an application in the food and restaurant domain, has been developed and evaluated through a user study. Its results suggest that reasonably good systems can be developed with HRIChat. This paper also reports lessons learned from the development and evaluation of FoodChatbot.