Data Set Generation for the Attributes of the Words of the Holy Quran: Information Retrieval System for E-Learning

摘要

This paper aims to enlightening a unique technique influenced by modern methodologies of advanced learning implemented in various domains of knowledge. Faster communication and manipulation of data are the aspects of IT that contribute lot to the learning minds by keeping the continuity and captivating the learner to absorb more and more in efficient manner. Harvesting these qualities of IT and merging it for easier, better and structured learning of holy Quran is the main objective of this paper. Arabic language in general and dialectal of holy Quran in particular is under the focus of many researchers in the field of Natural Language Processing (NLP). Arabic has morphology that differs from English in very basic level but it does follow systematic pattern when inflectional or derivational morphology is discussed. The challenges in the structuring of such a vast variety of data and their successful accomplishment are also added in brief but strengthen with examples to provide the depth of work carried out in this domain. Initially 23 attributes per word are applied to Quranic words (70% of words are covered till to date) based on Arabic parts of speech. These attributes are defined in such manner that language hierarchy is conserved to its maximum. The said application can be further enhanced to micro level data structuring. This effort did lead to implementation of information retrieval system that provides the proper tagging to each step. This approach can be further utilised in the field of Quranic education and research.