ToCT: A task ontology to manage complex templates

Mahlaza, Z and Keet, CM (2021) ToCT: A task ontology to manage complex templates, Proceedings of FOIS 2021 Ontology Showcase, part of JOWO'21, 13-16 September 2021, Bolzano, Italy and online, CEUR-WS, 2969, 9.

Text paper40-FoisShowCase.pdf Download (746kB)

Abstract

Natural language interfaces are a well-known approach to grant non-experts access to semantic web technologies. A number of such systems use simple templates to achieve that for English and more elab-orate solutions for other languages. They keep being designed from scratch in an ad hoc manner, since there is no shared conceptualisation of simple templates and there is no model that is formalised using a Semantic Web language to apply the techniques to itself. We aim to address this by proposing a general-purpose solution in the form of a novel model for templates, formalised as a task ontology in OWL,calledToCT. We used it to develop an ontology-driven text generator for isiZulu, a morphologically-rich language, to test its capabilities. The generator verbalises the TBox of an ontology as validationq uestions. This evaluation showed that the task ontology is sufficiently expressive for the template design, which was subsequently verified with user evaluations who judged the texts positively

Item Type:	Conference paper
Subjects:	Computing methodologies > Artificial intelligence > Natural language processing > Natural language generation Computing methodologies > Artificial intelligence > Knowledge representation and reasoning > Ontology engineering
Alternate Locations:	http://ceur-ws.org/Vol-2969/
Date Deposited:	03 Dec 2021 10:58
Last Modified:	03 Dec 2021 10:58
URI:	https://pubs.cs.uct.ac.za/id/eprint/1475

Actions (login required)

View Item