The impact of traditional and interactive post-editing on Machine Translation User Experience, quality, and productivity
Vicent Briva-Iglesias, Sharon O’Brien, Benjamin R. Cowan
Translation, Cognition and Behaviour
SALIS
Abstract

Neural Machine Translation has reached quality levels that have enabled users outside the translation industry to start incorporating the technology into their day-to-day working lives. Most studies in the area to date have focused mainly on translating more content in less time and with less effort, and little attention has been paid to user experience when interacting with the technology. This DCU research collaboration, we propose that the concept of Machine Translation User Experience (MTUX) should be given higher priority. 

The study and better understanding of MTUX will serve to help in the development or design of new technological systems for the language services industry or global multilingual communication and for better translator computer interaction.

This paper presents a user study with 15 professional translators in the English-Spanish combination. Results suggest that translators prefer IPE to TPE because they are in control of the interaction in this new form of translator-computer interaction and feel more empowered in their interaction with Machine Translation. Productivity results also suggest that IPE may be an interesting alternative to TPE, given the fact that translators worked faster in IPE even though they had no experience in this new machine translation post-editing modality, but were already used to TPE.