Arabic Document Summarization Using Fa Fuzzy Ontology

Ontology is the basis of sharing and reusing knowledge on the semantic web. The fuzzy ontology is an extension of the domain ontology for solving the uncertainty problems. Although many earlier methods tried to create a fuzzy ontology and applied it to documents summarization, none of the previous methods have discussed Arabic document summarization using FA fuzzy ontology which could benefit future research. This paper presents a new technique for Arabic document summarization using a fuzzy ontology, which is a fuzzy linguistic variable ontology and Field Association (FA) words. It is more suitable to describe fuzzy linguistic variable ontology than domain ontology for solving the uncertainty reasoning problem. At first, the domain ontology with various events Arabic language is predefined. The document preprocessing mechanism generates the meaningful terms based on Arabic corpus and Arabic language dictionary defined by the domain expert. Then, the meaningful terms have been classified according to an FA term classifier algorithm. Every fuzzy concept has a set of membership degrees associated with various events of the domain ontology. In addition, some process based on the fuzzy ontology is also developed for Arabic document summarization. From the experimental results, it is clear that the average of summarization accuracy achieved 69%, 68% and 68% in terms of Recall, Precision and F-measure. The results show that the Arabic document based on FA words and fuzzy ontology can effectively operate for summarization. Moreover, our new method using FA fuzzy ontology (FAFO) technique could be improved by 30-35% in terms of Recall, Precision and F-measures than traditional methods.