AN ARABIC FACTOID QUESTION ANSWERING SYSTEM USING USER PERSONAL PROFILE

Personalized content retrieval either for the Information Retrieval (IR) task or the Question Answering (QA) task aims at enhancing the retrieval process by complementing explicit user requests with implicit user preferences, to better meet individual user needs. It is appropriate to not only consider each user s queries/ searches in an isolated manner, but also to take into account the surrounding contextual information available from prior sets of user actions, by filtering and focusing the knowledge about user preferences on the semantic context of ongoing user activities, so as to achieve a coherence with the scope of user actions at runtime. Attempts in Arabic language to implement QA systems are scare, even without the raised issues of semantics and personalization. The aim of this research is to present a new Arabic factoid-QA system. This system will keep track of the information available from prior sets of user actions, and relate these personalized user preferences semantically to the current runtime user interests, in order to enhance the retrieval process