Arabic Search Engines Improvement: A New Approach using Search Key Expansion Derived from Arabic Synonyms Structure
H.K. Al Ameed, S.O. Al Ketbi, A.A. Al Kaabi, K.S. Al Shebli, N.F. Al Shamsi, Noura Al Nuaimi, S.S. Al Muhairi · IEEE International Conference on Computer Systems and Applications, 2006. · 2006
In both writing and conversation, different people may use different terminologies for the same concept. The same situation could be generalized on issuing queries for search engines and digital libraries. Arabic Information Retrieval (IR) systems practices are still based on word-matching rather than word-sense approaches. This paper addresses some characteristics of Arabic language text properties and its computer processing, in addition to a general idea about synonyms facility and its current implementation fields in IT. The study exhibits an implementation model for a new IR system using additional components like Arabic light stemmers and word synonyms structure which assist in solving some limitations that today’s Arabic IR systems suffer from. The study recommends the use of word stemming and wildcard search modules to solve the word scripts mismatching problem which arise with word-matching approach. In addition, it utilizes the synonyms facility in order to expand the queries in word-sense approach.