Term extraction using hybrid fuzzy particle swarm optimization

Abstract

Term extraction is one of the layers in the ontology development process, which has the task to extract all the terms contained in the input document automatically. The objective of this process is to generate a list of terms that are relevant to the domain of the input document. In this study, we present a hybrid method for improving the precision term extraction using a combination of Continuous Particle Swarm Optimization (PSO) and Discrete Binary PSO (BPSO) to optimize fuzzy systems. In this method, PSO and BPSO are used to optimize the membership functions and rule sets of fuzzy systems, respectively. The method was applied to the domain of tourism documents and compared with other term extraction methods: TFIDF, Weirdness, GlossaryExtraction and TermExtractor. From the experiment conducted, the combination of PSO-BPSO showed their capability to generate an optimal set of parameters for the fuzzy membership functions and rule sets automatic adjustment. Findings also showed that fuzzy system performance after optimization achieved significant improvements compared with that before optimization and gave better results compared to those four algorithms.