Object-Oriented Universal Grammar-Based Machine Translation (UGBMT)

This paper presents an object-oriented model for machine translation based on Universal Grammar, the Universal Lexicon and language-specific grammars and the lexicons, and demonstrates the internal structures of these linguistic constructs by following a step-by-step process of English to Japanese translation. It elucidates what elements are required in the Universal Lexicon and the lexicons of individual languages. The present model parses and generates sentences at three levels of structures: S-structure (Surface Structure), Istructure (Intermediary Structure) and U-Structure (Universal Structure). The present paper demonstrates the interaction of the three levels of structures in the process of translation, showing how economy and efficiency are achieved by incorporating the modules of Universal Grammar and the Universal Lexicon into the model of machine translation. This design makes each language grammar slim, distinguishing idiosyncrasies from elements of universal nature.