Jordanian Journal of Computers and Information Technology | 卷:1 |
A HYBRID APPROACH FOR INDEXING AND SEARCHING THE HOLY QURAN | |
Monther Tarawneh1  Emad Al-Shawakfa1  | |
[1] CIS Department, Faculty of IT, Yarmouk University, Irbid, Jordan; | |
关键词: Arabic NLP; IR; Quran; Keyword search; Semantic search; | |
DOI : 10.5455/jjcit.71-1445981961 | |
来源: DOAJ |
【 摘 要 】
Searching and retrieving information from the Holy Quran has recently received special attention by Muslim and Arab researchers. Many applications and websites offered to perform search through the Quran using keywords, semantic search, or even both. Arabic; as the language of the Quran, is having a complex structure and thus the searching process of Arabic scripts is rather more difficult than English. In this paper, we propose a hybrid approach; using a combination of syntactic (keyword) and word semantics, to search through the Quran text. The Quran text was pre-processed and represented in a XML format. A system was implemented using Python where the concept of regular expressions is used to test the approach with a Graphical User Interface used to manipulate user requests. Good and promising results from the approach were obtained.
【 授权许可】
Unknown