Arabic Expert System Shell

Arabic Expert System Shell

Venus Samawi1, Akram Mustafa1, and Abeer Ahmad2
1Department of Computer Science, Al-albayt University, Jordan
2Department of Computer Science, AL-Nahrain University, Iraq
 

Abstract:
Most expert system designers suffer from knowledge acquisition complications. Expert system shells contain facilities that can simplify knowledge acquisition to make domain experts themselves responsible for knowledge structuring and encoding. The aim of this research is to develop an Arabic Expert System Shell (AESS) for diagnosing diseases based on natural language. The suggested AESS mainly consists of two phases. The first phase is responsible for automatic acquiring of human expert knowledge. The acquired knowledge is analyzed by Arabic morphological system. The Arabic morphological system analyzes the given Arabic phrase and finds the required keywords (roots). The suggested system is provided with the required domain dictionary to be used by the Arabic morphological system. The second phase is concerned with the design of inference engine together with user interface (based on natural language) that uses a backward chaining method (end-user interface).When AESS tested by experts and end users, it was found that AESS performance in constructing Knowledge-Base (KB) and diagnosing problems was very exact (the diagnostic ability of AESS is 99%.). Merging of morphological system with knowledge acquisition is very effective in constructing the target KB without any duplicate or inconsistent rules. The same technique could be used to build expert system shell based on any other natural language (English, French, etc.). The only difference is to build morphological system suitable to that language in addition to the desired domain dictionary. 


Keywords: Expert system, knowledge acquisition, knowledge engineering, diagnosing expert system, Arabic morphological system.
 
Received October 25, 2010; accepted March 1, 2011
Read 3867 times Last modified on Monday, 07 January 2013 04:26
Share
Top
We use cookies to improve our website. By continuing to use this website, you are giving consent to cookies being used. More details…