A proposed model for Quranic Arabic WordNet

Most recent Arabic language computing research focuses on modern standard Arabic, but the classical Arabic of the Qur’an has been relatively unexplored, despite the importance of the Qur’an to Islam worldwide which can be used by both scholars and learners.This research work proposes to develop a WordNet for Qur’an by building semantic connections between words in order to achieve a better understanding of the meanings of the Qur’anic words using traditional Arabic dictionaries and a Qur’an ontology. The Qur’an corpus will be used as text and Boundary Annotated Qur’an Corpus (Brierley et al, 2012) will be used to explore the root and Part-of-Speech for each word and the word by word English translations. Traditional Arabic dictionaries will be used to find the Arabic meaning and derived words for each root in the Qur'anic Corpus. Then, these words and their meanings (Arabic, English) will be connected together through semantic relations. The achieved Qur’anic WordNet will provide an integrated semantic Qur’anic dictionary for the Arabic and English versions of the Qur'an.