Islamic Application of Question Answering Systems: Comparative Study

Abstract

A question answering system is a special type of information retrieval system [1] that retrieves relevant short answers that match the question, instead of retrieving relevant full documents in a standard information retrieval system. In this study, we use three prototypes uses different resources for answers: MS Access database in prototype1, text files in prototype2 and prototype3, for storing results, each of which is one verse (Ayah) from two chapters of the holy Quran: AlBagarah and AlFati'hah. Prototype1 uses an MS Access database and rule-based system for retrieving matching answers after removing stop words and diacritics from the input Arabic question. Prototype2 and Prototype3 use indexed text files and the Lucene search engine and its techniques, adapted to deal with our Arabic text corpus. These systems accept a question in natural language form, then search for the relevant answers from the text files. We evaluated the Prototypes with thirty questions about the Quran, chosen randomly. The answers were evaluated by Quran scholars from Gabrah educational college. There are many variations in results depending on many factors such as stemming, stop words used, etc. We conclude by comparing each system’s benefits and drawbacks.