Understanding Translationese in Multi-view Embedding Spaces

Proceedings of the 28th International Conference on Computational Linguistics, pages 6056–6062 Barcelona, Spain (Online), December 8-13, 2020 6056 Understanding Translationese in Multi-view Embedding Spaces Koel Dutta Chowdhury Saarland University koeldc@lst.uni-saarland.de Cristina Espa˜na-Bonet DFKI GmbH, Saarbr¨ucken cristinae@dfki.de Josef van Genabith Saarland University DFKI GmbH, Saarbr¨ucken Josef.Van Genabith@dfki.de Abstract Recent studies use a combination of lexical and syntactic features to show that footprints of the source language remain visible in translations, to the extent that it is possible to predict the original source language from the translation. In this paper, we focus on embedding-based se- mantic spaces, exploiting departures from isomorphism between spaces built from original target language and translations into this target language to predict relations between languages in an unsupervised way. We use different views of the data — words, parts of speech, semantic tags and synsets — to track translationese. Our analysis shows that (i) semantic distances between original target language and translations into this target language can be detected using the notion of isomorphism, (ii) language family ties with characteristics similar to linguistically motivated phylogenetic trees can be inferred from the distances and (iii) with delexicalised embeddings exhibiting source-language interference most significantly, other levels of abstraction display the same tendency, indicating the lexicalised results to be not “just” due to possible topic differ- ences between original and translated texts. To the best of our knowledge, this is the first time departures from isomorphism between embedding spaces are used to track translationese. 1 Introduction The term “translationese” refers to systematic differences between translations and text originally au- thored in the target language of the translation, in the same genre and style (Gellerstam, 1986; Baker and others, 1993; Baroni and Bernardini, 2005; Volansky et al., 2015). Characteristics such as simplification, over-adherence to conventions of the target language, and explicitation can occur as a communicative process itself. This is contrasted with “interference” or “shining-through” (Teich, 2003), described as “phenomena pertaining to the make-up of the source text tend to be transferred to the target text” (Toury, 2012). Prominent evidence for shining-through as a translationese effect is found in the work of Rabi- novich et al. (2017), who show that footprints of the source language remain visible in translations, to the extent that it is possible to predict the original source language from the translation. In the similar vein, a significant amount of work has gone into training classifiers to distinguish between translations and originally authored text and then investigating the contributions of individual features to the result of the classification (Baroni and Bernardini, 2005; Koppel and Ordan, 2011; Volansky et al., 2015; Avner et al., 2016). Features that contribute strongly to classification are interpreted as indicating important dimensions of translationese. In contrast, in this work, we leverage departures from isomorphism between embedding-based seman- tic spaces to detect translationese. We construct embedding spaces from original English (O) data and translations into English (T) from comparable data in a number of languages. We hypothesize that the closer the source language is to English, …

Content truncated to 500 words