Investigating translated Chinese and its variants using machine learning

Abstract

Translations are generally assumed to share universal features that distinguish them from texts that are originally written in the same language. Thus, we can argue that these translations constitute their own variety of a language, often called translationese. However, translations are also influenced by their source languages and thus show different characteristics depending on the source language. Consequently, we argue that these variants constitute different “dialects” of translations into the same target language. Studies using machine learning techniques on Indo-European languages have investigated the universal characteristics of translationese and how translations from various source languages differ. However, for typologically very different languages such as Chinese, there are only few corpus studies that tap into the intricate relation between translations and the originals, as well as into the relations among translations themselves. In this contribution, we investigate the following questions: (1) What are the characteristics of Chinese translationese, both in general and with respect to different source languages? (2) Can we find differences not only at the lexical but also on the syntactic level? and (3) Based on the characteristics found in the previous questions, which of the proposed laws and universals can we corroborate based on our evidence from Chinese? We use machine learning to operationalize determining the importance of different characteristics and comparing their importance for our Chinese dataset with characteristics previously reported in studies on English. In addition, our methodology allows us to add syntactic features, which have rarely been used to study translations into Chinese. Our results show that Chinese translations as a whole can be reliably distinguished from non-translations, even based on only five features. More interestingly, typological traces from the source languages can often be found in their translations, therefore creating what we call dialects of translationese. For instance, translations from two Altaic languages exhibit more noun repetition and less frequent use of pronouns. Additionally, some characteristics that are not discriminative for English work well for Chinese, possibly because the distance between Chinese and the source languages is greater than that in English studies.

Building a Treebank for Chinese Literature for Translation Studies

“…Apart from the two new tags we created for suffixes (SFE and SFP), there are two tags that occur in TCL original but not in CTB: IJ (interjection) and ON (onomatopoeia), both typical for colloquial expressions. From the POS distribution of TCL translated , in contrast, we see that translated Chinese overuses pronouns (PN), prepositions (P) and the marker 的(DEG), confirming the results from previous translation studies in Chinese (Xiao and Hu, 2015;Hu and Kübler, 2020).…”

“…LCMC has been widely used in linguistic studies of Chinese (Duanmu, 2012;Song and Tao, 2009;Zhang, 2017). Similarly, ZCTC is considered a standard resource for translation studies in Chinese (Xiao, 2010;Xiao and Hu, 2015;Hu and Kübler, 2020).…”

“…Second, in translation studies, a well-known hypothesis states that translated texts are lexically and syntactically simpler than texts originally written in a language (Baker, 1993;Baker, 1996). Empirical results of this simplification hypothesis have been mixed (Laviosa-Braithwaite, 1996;Ilisei and Inkpen, 2011;Volansky et al, 2013;Hu and Kübler, 2020). TCL can provide a high quality data source for evaluating this hypothesis.…”

“…We plan to use the parser to extend prior work on translationese(Hu and Kübler, 2020;Lin, 2017;Lin and Hu, 2018) to the domain of literature.2 We use "literary Chinese" to mean Chinese in the domain of literature, rather than "classical Chinese", which is sometimes also referred to as "literary Chinese".…”

OCNLI: Original Chinese Natural Language Inference

“…One issue concerns limitations in the quality of automatic translations, resulting in incorrect or unintelligible sentences (e.g., see Table 2b). But even if the translations are correct, they suffer from "translationese", resulting in unnatural language, since lexical and syntactic choices are copied from the source language even though they are untypical for the target language (Koppel and Ordan, 2011;Hu and Kübler, 2020).…”