NMT verb rendering: A cognitive approach to informing Arabic-into-English post-editing

Abstract

Machine translation (MT) has made significant strides and has reached accuracy levels that often make the post-editing (PE) of MT output a viable alternative to manual translation. However, despite professional translators increasingly considering PE as a valid stage in their translation workflow, little has been done to investigate MT output for the purpose of informing training in PE. Against this background, the present project focuses on the handling of tense and aspect configurations in the English translation of Arabic sentences using current neural machine translation (NMT) systems. Using a dataset of representative Arabic sentences, the output of five NMT engines was assessed against reference translations. The investigation reveals regressing accuracy levels when comparing morphological, structural, and contextual tenses. These findings are believed to represent valuable information that contributes to a more informed training in the PE of Arabic-into-English NMT output.

Systematic Review of English/Arabic Machine Translation Postediting: Implications for AI Application in Translation Research and Pedagogy

“…Ref. [25] reported that Systran, Reverso, and Yandex achieved similar results in terms of accuracy. Other studies focused on different types of meanings.…”

“…MTPE is a digital literacy that still awaits due attention in the academic and professional practice of English/Arabic translation, considering the growing demand for translation and the increased use of MT among translators and translation students. While some research studies have underscored the popularity and recent surge in MTPE practice among users and translation service providers [22][23][24], there is humble recognition of postediting by translation communities, academic programs, and research in the English/Arabic language pair [25][26][27][28].…”

“…Ref. [25] tested the accuracy of NMT in rendering the linguistic features of tense and aspect to inform Arabic-into-English MTPE curricula and training.…”

A Cognitive Approach to Machine Translation Post-editing of English-Arabic Literary Texts

“…They could be classified into two main approaches: physiological sensor-based and translation accuracybased approaches. Moorkens (2018), Herbig, Pal, Vela, Krüger, and van Genabith (2019) and (2021), as well as Almanna, Jamoussi, (2022) are among the scholars who extensively investigate the issue of cognitive load during MT post-editing.…”