Conversational control interface to facilitate situational understanding in a city surveillance setting

Harborne, Daniel, Braines, David, Preece, Alun ORCID: https://orcid.org/0000-0003-0349-9057 and Rzepka, Rafal 2018. Conversational control interface to facilitate situational understanding in a city surveillance setting. Presented at: The fourth Linguistic and Cognitive Approaches to Dialog Agents Workshop (LACATODA 2018), Stockholm, Sweden, 13 Jul 2018. Published in: Rzepka, R., Vallverdu, J. and Wlodarczyk, A. eds. Proceedings of the Linguistic and Cognitive Approaches To Dialog Agents Workshop. pp. 59-66.

Preview

PDF - Accepted Post-Print Version Download (7MB) | Preview

Abstract

In this paper we explore the use of a conversational interface to query a decision support system pro- viding information relating to a city surveillance setting. Specifically, we focus on how the use of a Controlled Natural Language (CNL) can provide a method for processing natural language queries whilst also tracking the context of the conversation with relation to past utterances. Ultimately, we pro- pose our conversational approach leads to a versa- tile tool for providing decision support with a low enough learning curve such that untrained users can operate it either within a central command location or when operating within the field (at the tactical edge). The key contribution of this paper is an il- lustration of applied concepts of CNLs as well as furthering the art of conversational context tracking whilst using such a technique. Keywords: Natural Language Processing (NLP), Conversational Systems, Situational Understanding

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Subjects:	T Technology > T Technology (General)
ISSN:	1613-0073
Projects:	DAIS ITA
Date of First Compliant Deposit:	17 July 2018
Last Modified:	06 Aug 2026 14:45
URI:	https://orca.cardiff.ac.uk/id/eprint/113152

Citation Data

Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item