An Evaluation of Output Quality of Machine Translation Program

This article reports an exploratory evaluation of the output quality of two prevalent English-Persian Machine Translation programs. The purpose of the research is to find out which program produces relatively better output, and what major linguistic bottlenecks MT programs will encounter in their processing of texts. Criteria were established in light of structural theories to solve the MT output from the perspective of Accuracy and Intelligibility. For each program, the mean score it obtained for its output and the rate of correctness of its translation of the testing points were calculated. An analysis of the mean score and the rate of correctness of each program generated the following findings about the output quality of these two programs: 1) Padideh Translator produces the best output. 2) The major linguistic bottlenecks in English-Persian MT programs occur in the areas of morphology, complex sentences, syntactic ambiguity and semantic analysis, generation of Persian, and long sentences.