Towards a bidirectional machine translator generator for multilingual communication

Machine Translation (MT) systems are typically quite complex, especially those used in production environments where high-quality conversational text or speech translation from one language to another is important. As a result, the vast majority of MT systems support translation between a single language pair, often uni-directionally. This research study extends previous work to assess the efficacy of developing a bidirectional translator generator in Prolog programming language using Lexical Functional Grammars. The main research objective is building a machine translator generator for multilingual communication, i.e. developing a system whose inputs are linguistic descriptions of a desired source and target language and whose output is a program that translates between the two natural languages. The implementation of a bidirectional machine translator between English and Hungarian, developed as a proof-of-concept case study, is discussed and assessed in terms of four general classes of translation. The benefits and drawbacks of this approach as generalized to MT systems are also discussed, along with possible areas of future work.