Detecting Language Features of ‘Machine-Translationese’ through Machine Learning: Original Chinese News Text vs. Machine-Translated Chinese News Text

Date:

Abstract:
This presentation investigates the linguistic features of “Machine-Translationese” (MTese) in English-to-Chinese machine-translated news texts. Through machine learning approaches, we identify and quantify distinctive characteristics that differentiate machine-translated Chinese news texts from originally authored Chinese news texts. Our methodology employs clustering techniques to visualize these differentiating features, revealing systematic patterns in MTese.

Key aspects:

  • Comparative analysis of original vs. machine-translated Chinese news texts
  • Identification of quantifiable MTese markers in English-Chinese translation
  • Machine learning-based clustering for feature visualization
  • Implications for machine translation evaluation and quality assessment