Translating away Translationese without Parallel Data
Submission Type: Regular Long Paper
Submission Track: Multilinguality and Linguistic Diversity
Submission Track 2: Machine Translation
Keywords: Translationese Mitigation, Text Style Transfer, Unsupervised Training, Bias Mitigation
TL;DR: This work focuses on reducing translationese in translated texts, aiming to bring them closer in style to the originally-authored ones. We introduce a translation-based style transfer approach that does not rely on the availability of parallel data.
Abstract: Translated texts exhibit systematic linguistic differences compared to original texts in the same language, and these differences are referred to as translationese. Translationese has effects on various cross-lingual natural language processing tasks, potentially leading to biased results. In this paper, we explore a novel approach to reduce translationese in translated texts: translation-based style transfer. As there are no parallel human-translated and original data in the same language, we use a self-supervised approach that can learn from comparable (rather than parallel) mono-lingual original and translated data. However, even this self-supervised approach requires some parallel data for validation. We show how we can eliminate the need for parallel validation data by combining the self-supervised loss with an unsupervised loss. This unsupervised loss leverages the original language model loss over the style-transferred output and a semantic similarity loss between the input and style-transferred output. We evaluate our approach in terms of original vs. translationese binary classification in addition to measuring content preservation and target-style fluency. The results show that our approach is able to reduce translationese classifier accuracy to a level of a random classifier after style transfer while adequately preserving the content and fluency in the target original style.
Submission Number: 1078
Loading