How does machine translation affect language? : analyzing the effect of machine translation on translated texts

Abstract

This Master Thesis analyses the effect of neural machine translation on the language of the translation in terms of lexical, morphological, and syntactical diversity or richness. Four neural machine translation models are trained. Two different corpora of similar length and domain, one of which was created in this work, are used to train and evaluate the models, as well as translate text. Two language pairs were used in both directions: English and Spanish; and English and Croatian. Regarding lexical richness, the majority of our results indicate a degree of lexical loss in the translations. One metric shows a gain of lexical diversity in one of the translations. In morphological richness, the results are not as clear, with most of the metrics showing slight to no loss, or even a gain of richness in two of the translations. Part of speech distribution analysis, as well as parse distribution analyses, both seem to confirm claims made by some that neural machine translation systems increase the frequency of most and decrease the frequency of least frequent items.