Computational analysis of different translations: by professionals, students and machines

In this work, we analyse translated texts in terms of various features. We compare two types of human translations, professional and students’, and machine translation (MT) outputs in terms of lexical and grammatical variety, sentence length, as well as frequencies of different part-of-speech (POS) tags and POS-trigrams. Our analyses are carried out on parallel translations into Croatian, Finnish and Russian, all originating from the same source English texts. Our results indicate that machine translations are the closest to the source text, followed by student translations. Also, student translations are sometimes more similar to MT than to professional translations. Furthermore, we identify sets of features distinctive for machine translations