On the features of translationese

Much research in translation studies indicates that translated texts are ontologically different from original, non-translated ones. Trans-lated texts, in any language, can be considered a dialect of that lan-guage, known as ‘translationese’. Several characteristics of transla-tionese have been proposed as universal in a series of hypotheses. In this work we test these hypotheses using a computational methodol-ogy that is based on supervised machine learning. We define several classifiers that implement various linguistically-informed features, and assess the degree to which different sets of features can distinguish be-tween translated and original texts. We demonstrate that some feature sets are indeed good indicators of translationese, thereby corroborating some hypotheses, whereas others perform much worse (sometimes at chance level), indicating that some ‘universal ’ assumptions have to be reconsidered. 1