Enhancing Conversational Troubleshooting with Multi-modality: Design and Implementation
Giulio Antonio Abbo, Pietro Crovari and Franca GarzottoTL;DR
This work extends MCTK by making it a plug and play component with multilingual support thanks to NPL.js.
Abstract
Conversational troubleshooting is an increasingly popular technology that consists in utilising dialogue agents to support users of a system through a conversation-based question-answering process, typically through a chatbot. Despite their widespread use, current troubleshooting technologies lack a thorough integration with the applications on which they are overlaid, as they rely only on text to help the users. In this paper, we present TINI, an open-source conversational troubleshooting tool that is multi-modal and multilingual, relies on simple configuration files, and is ready to be deployed in web applications. Users can ask questions to the conversational agent explaining the issue faced; the system analyses it together with the interaction’s context to locate the root problem. Finally, it proposes a solution which engages the user multi-modally: with text in the chat and hints in the graphical interface. A table-based configuration improves system maintainability and enables dialogue designers and field experts to work on the conversation without any coding experience required.
ACM Reference
Giulio Antonio Abbo, Pietro Crovari, and Franca Garzotto. 2023. Enhancing Conversational Troubleshooting with Multi-modality: Design and Implementation. In Chatbot Research and Design (CONVERSATIONS '22). Springer International Publishing, Cham, 103–117. https://doi.org/10.1007/978-3-031-25581-6_7BibTeX
@InProceedings{10.1007/978-3-031-25581-6_7,
author="Abbo, Giulio Antonio
and Crovari, Pietro
and Garzotto, Franca",
editor="F{\o}lstad, Asbj{\o}rn
and Araujo, Theo
and Papadopoulos, Symeon
and Law, Effie L.-C.
and Luger, Ewa
and Goodwin, Morten
and Brandtzaeg, Petter Bae",
title="Enhancing Conversational Troubleshooting with Multi-modality: Design and Implementation",
booktitle="Chatbot Research and Design",
year="2023",
publisher="Springer International Publishing",
address="Cham",
pages="103--117",
abstract="Conversational troubleshooting is an increasingly popular technology that consists in utilising dialogue agents to support users of a system through a conversation-based question-answering process, typically through a chatbot. Despite their widespread use, current troubleshooting technologies lack a thorough integration with the applications on which they are overlaid, as they rely only on text to help the users. In this paper, we present TINI, an open-source conversational troubleshooting tool that is multi-modal and multilingual, relies on simple configuration files, and is ready to be deployed in web applications. Users can ask questions to the conversational agent explaining the issue faced; the system analyses it together with the interaction's context to locate the root problem. Finally, it proposes a solution which engages the user multi-modally: with text in the chat and hints in the graphical interface. A table-based configuration improves system maintainability and enables dialogue designers and field experts to work on the conversation without any coding experience required.",
isbn="978-3-031-25581-6"
}