Can college students be post-editors? An investigation into employing language learners in machine translation plus post-editing settings

Abstract

Despite the pressure to reduce costs in the advent of machine translation plus post-editing (PE), many professional translators are reluctant to accept PE jobs, which are perceived as requiring less skill and yielding poorer quality products than human translation (HT). This trend in turn raises an issue in the industry, namely, a lack of post-editors. To meet the growing demand for PE, new populations--such as college language learners--should be assessed as potential post-editor candidates. This paper investigates this possibility through an experiment focusing on college language learners' PE qualifications and resultant performance. Data collected on perceived ease of task, editing quantity, and quality of final product were correlated with the students' course grades. The investigation found that over 74 % of students felt PE to be an easier task than HT, whereas 26 % did not. Those students who did not find PE easier were determined to be unqualified post-editors. Students who received poor grades in a traditional translation course were also confirmed to be unqualified, though A-students were not always qualified post-editors. The variable performance among A-students may be understood in terms of different approaches to PE, characterized as utilizing either analytic or integrated processing. An analysis using this framework tentatively concludes that A-students who apply an analytic approach, more typical of novice translators, may perform better as post-editors than those who take an integrated approach.