Post-édition et traduction humaine en contexte académique une étude empirique

Main Article Content

Perrine Schumacher

Abstract

Today more than ever, translators must acquire new skills if they want to keep abreast of recent and future technological developments. The demand for machine translation (MT) post-editing (PE) has been growing steadily since 2017 and most PE work is being done by translators. Neural MT advances are clearly undeniable, but how does PE quality compare to that of human translation (HT)? To answer this question, we conducted a controlled experiment with translation students for the language pair English-French. In this paper, we present the results of the comparative analysis of our corpus after it was assessed by human evaluators. Our results showed, in particular, a higher success rate in PE of neural MT compared to both other methods (HT and PE of statistical MT), as well as a leveling effect in PE of neural MT.


Keywords: ¨Post-editing, Neural Machine Translation, Controlled Experiment, Translation Quality Assessment, Translation Students.

Downloads

Download data is not yet available.

Article Details

How to Cite
Schumacher, P. (2020). Post-édition et traduction humaine en contexte académique : une étude empirique. Transletters. International Journal of Translation and Interpreting, (4), 239–274. Retrieved from https://journals.uco.es/tl/article/view/12722
Section
Articles