Translationese and Its Dialects

TLDR

Translation produces distinct textual differences, attributed either to source‑language interference or to general translation processes. The study employs text‑categorization experiments to show that both source‑language interference and general translation effects exist and lie on a continuum. Translation effects are consistent across source languages and even language families, and a classifier can reliably distinguish translated from original texts across diverse languages and genres.

Abstract

While it is has often been observed that the product of translation is somehow different than non-translated text, scholars have emphasized two distinct bases for such differences. Some have noted interference from the source language spilling over into translation in a source-language-specific way, while others have noted general effects of the process of translation that are independent of source language. Using a series of text categorization experiments, we show that both these effects exist and that, moreover, there is a continuum between them. There are many effects of translation that are consistent among texts translated from a given source language, some of which are consistent even among texts translated from families of source languages. Significantly, we find that even for widely unrelated source languages and multiple genres, differences between translated texts and non-translated texts are sufficient for a learned classifier to accurately determine if a given text is translated or original.