Final published version, 228 KB, PDF document
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Effectiveness of query expansion in searching the Holy Quran
AU - Hammo, Bassam
AU - Sleit, Azzam
AU - El-Haj, Mahmoud
PY - 2007
Y1 - 2007
N2 - Modern 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 user’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.
AB - Modern 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 user’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.
KW - Arabic Information Retrieval
KW - Searching the holy Quran
KW - Diacritic Text
KW - Question Answering Systems
KW - Arabic Stemming
KW - Arabic Thesaurus
M3 - Conference contribution/Paper
SP - 1
EP - 10
BT - The Second International Conference on Arabic Language Processing CITALA'07
CY - Rabat, Morocco
ER -