The Professional Profile of a Post-editor according to LSCs and Linguists: a Survey-Based Research

The boundaries between translation technologies are fading and language professionals are heading towards a pluri- and transdisciplinary job description, for which the use of CAT tools, translation management systems, and machine translation (MT) are compulsory. “Language paraprofessionals”, “paralinguists”, “language consultants”, “digital linguists”, and a long list of other titles is emerging to refer to the professionals who master a number of features of several tools, while remaining attentive to linguistics (see Bond 2018). According to TAUS DQF Dashboard data presented in TAUS Newsletter the 1st of May of 2019, the industry averages show that 9.7% of the translation output origin comes from MT and that 1,057 words per hour are post-edited on average. This has clear repercussions on the profession from the employability perspective.With 66 submissions by LSCs and industry stakeholders, and 142 answers from individuals (in-house or freelance translators), we present the most salient subject matters from and for the translation industry regarding MT post-editing. Some represent gaps to be filled; others represent common ground already found. Thanks to this up-to-date knowledge of the globalization landscape, clear goals can be set, and the way is paved for evolution.

Language industry views on the profile of the post-editor

The more language service companies (LSCs) include machine translation post-editing (MTPE) in their workflows, the more important it is to know how the PE task is performed, who the post-editors are, and what skills they should have. This research is designed to address such questions. It aims to deepen our knowledge of current practices to later create new training content and adapt existing training methodologies to different types of audiences. Based on the results of a survey of LSCs and other companies who currently use MTPE, we present a picture of evolving practices in the contemporary European MTPE market, and opinions held about this emerging métier. Our research finds that a high level of expertise in MTPE may not necessarily be indicative of the industry, and that the post-editor of MT has a multi- and transdisciplinary profile.

Translation Quality and Error Recognition in Professional Neural Machine Translation Post-Editing

This study aims to analyse how translation experts from the German department of the European Commission’s Directorate-General for Translation (DGT) identify and correct different error categories in neural machine translated texts (NMT) and their post-edited versions (NMTPE). The term translation expert encompasses translator, post-editor as well as revisor. Even though we focus on neural machine-translated segments, translator and post-editor are used synonymously because of the combined workflow using CAT-Tools as well as machine translation. Only the distinction between post-editor, which refers to a DGT translation expert correcting the neural machine translation output, and revisor, which refers to a DGT translation expert correcting the post-edited version of the neural machine translation output, is important and made clear whenever relevant. Using an automatic error annotation tool and the more fine-grained manual error annotation framework to identify characteristic error categories in the DGT texts, a corpus analysis revealed that quality assurance measures by post-editors and revisors of the DGT are most often necessary for lexical errors. More specifically, the corpus analysis showed that, if post-editors correct mistranslations, terminology or stylistic errors in an NMT sentence, revisors are likely to correct the same error type in the same post-edited sentence, suggesting that the DGT experts were being primed by the NMT output. Subsequently, we designed a controlled eye-tracking and key-logging experiment to compare participants’ eye movements for test sentences containing the three identified error categories (mistranslations, terminology or stylistic errors) and for control sentences without errors. We examined the three error types’ effect on early (first fixation durations, first pass durations) and late eye movement measures (e.g., total reading time and regression path durations). Linear mixed-effects regression models predict what kind of behaviour of the DGT experts is associated with the correction of different error types during the post-editing process.

Post-editing quality: Analysing the correctness and necessity of post-editor corrections

Post-editing (PE) machine translations (MT) has become an increasingly common practice in the translation field in recent years. Research has investigated, among other issues, the types of error corrected by post-editors, but less emphasis has been placed on the corrections themselves and how they reflect MT errors. This article presents a pilot study analysing the edits made by five student post-editors in an English–Finnish post-editing task. We analyse the correctness and necessity of the edits. Our results show that, whereas most edits performed in the task are correct, a significant number of them (34%) are unnecessary. The findings suggest that specific types of edit, such as word-order changes and deletions of personal pronouns, are generally unnecessary for this language pair, which may have implications for post-editing practice and training.