Unsupervised Identification of Translationese

TL;DR

This paper presents an unsupervised method for accurately distinguishing translated texts from original ones across various domains, overcoming limitations of supervised classifiers and handling mixed-domain datasets effectively.

Contribution

It introduces a fully-unsupervised clustering approach with label determination and voting, improving translationese detection across diverse and mixed domains.

Findings

Unsupervised classification outperforms supervised methods outside training domains.

Labeling and voting strategies enhance clustering accuracy.

Effective clustering achieved even with mixed-domain datasets.

Abstract

Translated texts are distinctively different from original ones, to the extent that supervised text classification methods can distinguish between them with high accuracy. These differences were proven useful for statistical machine translation. However, it has been suggested that the accuracy of translation detection deteriorates when the classifier is evaluated outside the domain it was trained on. We show that this is indeed the case, in a variety of evaluation scenarios. We then show that unsupervised classification is highly accurate on this task. We suggest a method for determining the correct labels of the clustering outcomes, and then use the labels for voting, improving the accuracy even further. Moreover, we suggest a simple method for clustering in the challenging case of mixed-domain datasets, in spite of the dominance of domain-related features over translation-related ones. The result is an effective, fully-unsupervised method for distinguishing between original and translated texts that can be applied to new domains with reasonable accuracy.