Semantic search of Holy Quran using English Wordnet

This paper presents a framework to perform concept- and keyword-based English search of the Holy Quran. The concept-based search is challenging as it should be able to handle the abstract queries which often do not occur verbatim in text. In order to implement it, a Qur’anic English WordNet is implemented, which is a WordNet-derived database for the English translations of the Qur’an to form the basis of a semantically rich resource for Qur’an search system. WordNet structure of semantically linked information is used as baseline and is augmented with a few newly created relations to capture Qur’an specific information. A Vocabulary of Qur’anic Concepts is also automatically extracted from the English Qur’anic translations and is made available in the form of conceptual hierarchy. Finally, an information retrieval tool, Qur’an enhanced search tool, is developed to perform semantically enhanced search based on the newly created knowledge resources. The strength of the proposed scheme is demonstrated by comparing the information retrieved against other similar tools, and results are found to be encouraging with best performance in terms of recall. Furthermore, the semiautomatic approach of creating the knowledge repository used in this research is scalable as compared to other existing systems which are manually created. The proposed system is easily extendable for other religious knowledge texts such as Islamic Jurisprudence and Hadeeth.

Publication: https://link.springer.com/article/10.1007/s13369-018-03709-2