The interaction effect between source text complexity and machine translation quality on the task difficulty of NMT post-editing from English to Chinese: A multi-method study

Abstract This study explores the interaction effect between source text (ST) complexity and machine translation (MT) quality on task difficulty of neural (NMT) post-editing from English to Chinese. When investigating human effort exerted in post-editing, existing studies have seldom taken both ST MT levels into account, mainly focused systems used before emergence NMT. Drawing process product data 60 trainee translators, this adopted a multi-method approach measure difficulty, including eye-tracking, keystroke logging, evaluation, subjective rating, retrospective written protocols. The results show that: 1) present significant NMT post-editing; 2) level has positive impact low-quality (i.e., becomes less difficult when decreases); while for high-quality NMT, it only ratings received participants; 3) negative its goes higher), stronger increases. paper concludes that should be considered testing designing tasks post-editor training, setting fair pricing schemes.