Syntactic rule-based approach for extracting concepts from quranic translation text

Concept extraction is one of the important parts in ontology learning approach in order to construct ontology. This step becomes an inevitable process in such ontology development and becomes a seed to the next step in the approach. Studies in unstructured text especially in Malay are quite little due to the lack of availability extraction tools to extract relevant information. In addition, studies in Malay unstructured text based on Al-Quran is very rare compared to English and Arabic text. In this paper, an early experiment was carried out to extract concepts from Malay translation of Quranic texts using several rules-based formulated by Malaysian government body that responsible for Malay language. The study focuses only noun phrases in the Malay Quranic Text which involves only twenty- two short chapters or surah that comprises from Surah Ad-Dhuha to An-Nas. There are two criteria that have been tested in terms of symbols and stop words. The result of noun phrases has been extracted range from a combination of one word to twelve words. It shows that all the extracted noun phrases are not sufficient enough to extract most of the important concept in Al-Quran.