Extending a model for Ontology-Based Arabic-English Machine Transltion

Communication cannot happen effectively without Machine-Translation because they can be found anytime and everywhere. There is a number of research that has developed Machine-Translations and provides somehow precise translations between many languages and the English. However, translation to the Arabic language hasn't been considered to give us a precise translation yet. As a result, there's a necessity to enable the users to get a more corrected translation from and to the Arabic language than many of the previous works. Therefore, the aim of this work is to extend the Judge Method model of Arabic-English machine translation to provide a translation based on ontology and to illustrate its work. To evaluate this model, a sample dataset was established to be used for testing purposes. The used way to evaluate NAN final is the cosine similarity which can be used to evaluate the similarity between two texts after translation or summarization. The angle of similarity of NAN translation with human translation was approximately equals to 10.7 . Accordingly to that, NAN's angles is the smallest, better and corrector than Google's and Bing's.