Concept Extraction on Quranic Translation Text

Abstract

The Semantic knowledge that based on ontology learning technology introduced is to reduce the overall time of ontology construction. Ontology construction process includes several aspects and layers, and extraction domain concept is one of the most important aspects. This step becomes a prerequisite process in developing ontology and also becomes a seed to the next step. In this paper, we carried out several experiments based on linguistics, statistical and hybrid approaches in order to identify which are the best techniques and approaches to extract terms from Quranic translation text.  For linguistic approach, we used POS pattern, for statistical approaches, we choose seven frequency-based as the techniques to choose frequency terms and for hybrid, we combined both linguistic and statistical approaches. The results obtained show that the hybrid approach is the best in identifying and filtering relevant concepts in Quranic domain corpus.