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. 1

We investigate the differences between language models compiled from original target-language texts and those compiled from texts manually translated to the target language. Corroborating established observations of Translation Studies, we demonstrate that the latter are significantly better predictors of translated sentences than the former, and hence fit the reference set better. Furthermore, translated texts yield better language models for statistical machine translation than original texts. 1

We introduce a systematic approach to language change quantification by studying unconsciously used language features in time-separated parallel translations. For this purpose, we use objective style markers such as vocabulary richness and lengths of words, word stems and suffixes, and employ statistical methods to measure their changes over time. In this study, we focus on the change in Turkish in the second half of the twentieth century. To obtain word stems, we first introduce various stemming techniques and show that they are highly effective. Our statistical analyses show that over time, for both text and lexicon, the length of Turkish words has become significantly longer, and word stems have become significantly shorter. We also show that suffix lengths have become significantly longer for types and the vocabulary richness based on word stems has shrunk significantly. These observations indicate that in contemporary Turkish one would use more suffixes to compensate for the fewer stems to preserve the expressive power of the language at the same level. Our approach can be adapted for quantifying the change in other languages.