Improving Term Extraction Using Particle Swarm Optimization Techniques

TL;DR

This paper introduces a novel term extraction method using particle swarm optimization to enhance accuracy in domain-specific documents, outperforming existing algorithms in precision.

Contribution

The paper presents a new particle swarm optimization-based approach for term extraction, improving accuracy over traditional methods in the religious document domain.

Findings

Achieved higher precision than TFIDF, Weirdness, GlossaryExtraction, and TermExtractor.

Applied successfully to religious domain documents.

Demonstrated effectiveness of PSO in feature selection for term extraction.

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 purpose of this process is to generate list of terms that are relevant to the domain of the input document. In the literature there are many approaches, techniques and algorithms used for term extraction. In this paper we propose a new approach using particle swarm optimization techniques in order to improve the accuracy of term extraction results. We choose five features to represent the term score. The approach has been applied to the domain of religious document. We compare our term extraction method precision with TFIDF, Weirdness, GlossaryExtraction and TermExtractor. The experimental results show that our propose approach achieve better precision than those four algorithm.