Linguistic features of translated texts
Is translated language different from non-translated language? And if it is, can we tell which texts are translations, or even who translated them, simply by examining their linguistic features? Using a corpus of Finnish literary texts, I discuss how corpus linguistics and machine learning methods can be used to study the linguistic features that set translations apart from non-translations and distinguish translations from different source languages. The findings shed light on how linguistic features travel across languages and what translations can reveal about language contact and variation.
