Syntactic Open Domain Arabic Question/Answering System for Factoid Questions

Information Retrieval systems have become a crucial part of any search engine, taking into consideration the increased number of pages and documents added to the World Wide Web every day. Question/Answering systems are specific to retrieve the most accurate answer among several documents; this paper will present an improved methodology and implementation of an open domain Arabic Question Answering System for factoid questions. The proposed system is based on Query Expansion ontology and an Arabic Stemmer. Basically the system mainly depends on AWN as a semantic Query Expansion and Khoja stemmer as a stemming system, to evaluate the system we used 56 translated CLEF and TREC questions, four types of test scenarios are performed. Four evaluation attributes were considered: Accuracy, Mean Reciprocal Rank, Answered Questions and recall; and encouraging results were reached with the proposed system.