Résumé: The Qur’an is a fourteen centuries old divine book in Arabic language that is read and followed by almost two billion Muslims globally as their sacred religious text. With the rise of Islam, the Arabic language gained popularity and became the lingua franca for large swaths of the old world. Devout Muslims read the Qur’an daily seeking guidance and comfort. Though the Qur’an, as a text, is short, there is a huge volume of supporting work filling tens of thousands of volumes, e.g., commentaries, exegesis, etc. Recently, there has been a renewed interest in such religious texts by non-specialists. Many of which were fueled by the recent advances in computational and natural language processing (NLP) techniques. These techniques help the development of tools that benefit common people to gain knowledge easily. This paper surveys the different efforts in the field of Qur’anic NLP, serving as a synthesized compendium of works (tools, data sets, approaches) covering the gamut from automated morphological analysis to correction of Qur’anic recitation via speech recognition. Multiple approaches are discussed for several tasks, where appropriate. Finally, we outline future research directions in this field.

Langue: Anglais