Simplifying the Development of Conversational Speech Interfaces by Non-Expert End-Users Through Dialogue Templates

@Article {
title = {Simplifying the Development of Conversational Speech Interfaces by Non-Expert End-Users Through Dialogue Templates},
pages = {89-109},
keywds = {
Conversational speech interfaces; Dialogue templates; Task-oriented dialogue systems
}
abstract = {

Conversational speech interface development, maintenance and evolution is challenging for non-experts as it requires linguistic knowledge and proficiency in chatbot design and implementation. To address this issue, this work proposes the use of Dialogue Templates, compact conversational interfaces intended to cater specific interaction capabilities which can be easily adapted to a particular use case by non-expert end-users, just with knowledge of the application domain. Our implementation of Dialogue Templates is presented and detailed for three relevant conversational spoken interaction use cases in the industrial environment: navigating maintenance management systems, recording manufacturing plant activity data and registering warehouse inventory. In addition, a comparative analysis is also conducted to assess the effort required to develop sample conversational assistants in such scenarios using our conventional development platform versus Dialogue Templates. Results show that Dialogue Templates significantly simplify the development of conversational speech interfaces, without demanding linguistic expertise.

}
isbn = {978-303149424-6},
date = {2023-11-16},
}