Machine Translation (MT) for natural languages is considered one of the most interactive, complex and comprehensive application in the field of computational linguistics and artificial intelligence. And the Knowledge Based Machine Translation (KBMT) is very attractive and accurate approach when used for translation between Natural languages. This because of its knowledge base, which must contains the major morphological, syntactical, and semantical rules of the source and the target languages, which can overcome all the problems of analysis and generation processes. This paper presents a realistic technique for knowledge-based machine aided translation from English to Arabic. In this technique, the system dictionary is partitioned into multi-module structure for fast retrieval of Arabic features of English words. Each module is accessed through an interface that includes the necessary morphological rules, which directs the search toward the proper sub-dictionary. Another factor that aids fast retrieval of Arabic features of words is the prediction of the word category, and accesses its sub-dictionary to retrieves the corresponding attributes. The system consists of three main parts, which are the source language analysis, the transfer rules between source language (English) and target language (Arabic), and the generation of target language. The proposed system is able to translate (some negative forms, demonstrative nouns, conjunctive nouns, conjunctions, Arabic-Quai Sentence), and also adjusting nouns, verbs, and adjectives according their attributes. Then, it adds the symptom of Arabic word to generate a correct sentence. The system is implemented using Visual Basic Linked with Access Data Base in such a way that there could never be any confusion when used with its simple interface. |
