Fuzzy ontologies in semantic similarity measures

Chandran, D and Crockett, K (2016) Fuzzy ontologies in semantic similarity measures. In: 2016 IEEE Congress on Evolutionary Computation (CEC), 24 July 2016 - 29 July 2016, Vancouver, Canada.

Preview

Available under License In Copyright. Download (301kB) | Preview

Abstract

© 2016 IEEE. Ontologies are a fundamental part of the development of short text semantic similarity measures. The most known ontology used within the field was developed from the lexical database known as WordNet which is used as a semantic resource for determining word similarity using the semantic distance between words. The original WordNet does not include in its hierarchy fuzzy words - those which are subjective to humans and often context dependent. The recent development of fuzzy semantic similarity measures requires research into the development of different ontological structures which are suitable for the representation of fuzzy categories of words where quantification of words is undertaken by human participations. This paper proposes two different fuzzy ontology structures which are based on a human quantified scale for a collection of fuzzy words across six fuzzy categories. The methodology of ontology creation utilizes human participants to populate fuzzy categories and quantify fuzzy words. Each ontology is evaluated within a known fuzzy semantic similarity measure and experiments are conducted using human participants and two benchmark fuzzy word datasets. Correlations with human similarity ratings show only one ontological structure was naturally representative of human perceptions of fuzzy words.