Specifying and Staging Mixed-Initiative Dialogs with Program Generation and Transformation

TL;DR

This paper introduces a programming language-inspired notation and system for specifying and automatically generating flexible, mixed-initiative human-computer dialogs, streamlining their design and implementation.

Contribution

It presents a novel dialog specification notation based on programming language concepts and a system that automatically generates dialog implementations from these specifications.

Findings

Successfully automated dialog implementation from specifications

Demonstrated the notation's expressiveness for mixed-initiative dialogs

Provided a proof of concept for programming language-based dialog modeling

Abstract

Specifying and implementing flexible human-computer dialogs, such as those used in kiosks and smart phone apps, is challenging because of the numerous and varied directions in which each user might steer a dialog. The objective of this research is to improve dialog specification and implementation. To do so we enriched a notation based on concepts from programming languages, especially partial evaluation, for specifying a variety of unsolicited reporting, mixed-initiative dialogs in a concise representation that serves as a design for dialog implementation. We also built a dialog mining system that extracts a specification in this notation from requirements. To demonstrate that such a specification provides a design for dialog implementation, we built a system that automatically generates an implementation of the dialog, called a stager, from it. These two components constitute a dialog modeling toolkit that automates dialog specification and implementation. These results provide a proof of concept and demonstrate the study of dialog specification and implementation from a programming languages perspective. The ubiquity of dialogs in domains such as travel, education, and health care combined with the demand for smart phone apps provide a landscape for further investigation of these results.