# Enhancing Conversational Troubleshooting with Multi-modality: Design and Implementation

- Authors: Giulio Antonio Abbo, Pietro Crovari and Franca Garzotto
- Date: 2023-02-02
- Type: conference paper
- Venue: Chatbot Research and Design (LNCS, volume 13815) (CONVERSATIONS '22)
- DOI: https://doi.org/10.1007/978-3-031-25581-6_7
- Code: https://github.com/giubots/tini-mctk
- ResearchGate: https://www.researchgate.net/publication/367971687_Enhancing_Conversational_Troubleshooting_with_Multi-modality_Design_and_Implementation
- PDF: https://giubots.net/publications/enhancing-conversational-troubleshooting/enhancing-conversational-troubleshooting.pdf
- Research line: [Conversational Troubleshooting](https://giubots.net/research/conversational-troubleshooting/)
- URL: https://giubots.net/publications/enhancing-conversational-troubleshooting/


## TL;DR

This work extends MCTK by making it a plug and play component with multilingual support thanks to NPL.js.


This work extends [MCTK](publications/mctk-multi-modal) by making it a plug and play component with multilingual support thanks to [NPL.js](http://www.github.com/axa-group/nlp.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.

## How to cite

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_7

```bibtex
@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"
}
```