Smarter edits? Post-editing with error highlights and translation suggestions
For MT researchers and tool developers, this provides evidence that current error highlights do not boost efficiency, but correction suggestions may enhance user satisfaction.
The study tested whether LLM-derived error highlights and correction suggestions improve post-editing for professional translators, finding no productivity or quality gains over regular post-editing, though correction suggestions improved user experience.
As MT quality increases, interest in enhanced post-editing features such as QE-derived error highlights is growing, yet evidence for their usefulness remains limited. In this work, we explore the usefulness of LLM-derived error highlights and correction suggestions based on automatic post-editing (APE). We conduct a study where professional translators (En-Nl) post-edit translations using APE error highlights and correction suggestions and compare productivity, quality and user experience to regular PE and PE with QE-derived highlights. While no condition yielded productivity or quality gains compared to regular PE, APE highlights were better received than QE-derived highlights, and correction suggestions improved overall user experience.