translating medical texts from persian to english: accuracy of machine translation

Introduction: machine translation is a new subject increasingly being used by academic writers, especially students and researchers whose native language is not english. there have been numerous studies conducted on machine translation, but few investigations have assessed the accuracy of machine translation from persian to english at lexical, semantic, and syntactic levels.materials and methods: using groves and mundt’s model of error taxonomy, the current study evaluated persian-to-english translations produced by two famous online translators, google translate and bing translator. a total of 60 texts were randomly selected from the academic field of medicine. all texts were rendered by the two translation systems and then by four human translators. statistical analyses were applied using spss.results: the results indicated that google translations were more accurate than the translations produced by the bing translator in the domain of medicine (lexis: 186 vs. 225; semantic: 44 vs. 48; syntactic: 148 vs. 264 errors).conclusion: the findings suggest that students and researchers can reasonably benefit from the systems in rendering plain texts from persian to english, given that the translated versions are subjected to human editing.