SEMANTIC GRAPH KNOWLEDGE REPRESENTATION FOR AL-QURAN VERSES BASED ON WORD DEPENDENCIES

Semantic approaches present an efficient, detailed and easily understandable representation of knowledge from documents. Al-Quran contains a vast amount that needs appropriate extraction. A semantic based approach can help in designing efficient explainable model for Al-Quran. This research aims to propose semantic-graph verses on word dependencies. These features are used the proposed allowing graph matching improve search applications' accuracy. The is essentially formalism generating Quranic verses, which be applied base construction other applications such as information retrieval system. set rules called Dependency Triple Rules defined mapped into representing verse's logic. translate dependencies NLP metadata triple form holds logical information. has been tested with English translation document prototype basic system enhanced anaphoric pronouns correction, shown improvement performance. results have compared closely related evaluated accuracy Precision, Recall F-score measurements. achieved 65%, 60% 62.4% measurements, respectively. It also improved overall previous by 43.8%.