Conference Proceeding

Effectiveness of Query Expansion in Searching the Holy Quran

Sleit, Azzam, Hammo, Bassam, El Haj, Mahmoud

2007

Overview

Modem Arabic text is written without diacritical marks (short vowels), which causes considerable ambiguity at the word level in the absence of context. Exceptional from this is the Holy Quran, which is endorsed with short vowels and other marks to preserve the pronunciation and hence, the correctness of sensing its words. Searching for a word in vowelized text requires typing and matching all its diacritical marks, which is cumbersome and preventing learners from searching and understanding the text. The other way around, is to ignore these marks and fall in the problem of ambiguity. In this paper, we provide a novel diacritic-less searching approach to retrieve from the Quran relevant verses that match a use's query through automatic query expansion techniques. The proposed approach utilizes a relational database search engine that is scalable, portable across RDBMS platforms, and provides fast and sophisticated retrieval. The results are presented and the applied approach reveals future directions for search engines

• Publisher: معهد الدراسات والأبحاث للتعريب
• Subject: ألفاظ القرآن / القرآن الكريم / المؤتمرات والندوات / تفسير القرآن / مستخلصات الأبحاث