Post-editing is the process by which a human linguist revises raw machine-translated output to reach a specific quality level agreed with the client. In localization production, it is treated as a distinct service from revision or proofreading because the source text is first generated by an engine and the required effort depends heavily on the quality of the machine output.
Post-editing appears in translation projects where the client selects an MT engine, sets light or full post-editing rules, and expects the linguist to fix accuracy, grammar, style, or terminology issues. The instructions are recorded in project briefs, quality rubrics, and rate cards because effort varies by content and by MT output.
An evaluator may apply traditional revision standards and over-edit machine output, or accept fluent but inaccurate output because it reads smoothly. Both errors distort cost and quality: over-editing erases the productivity gain that justifies the workflow, and under-editing leaves factual errors or terminology mistakes in the published content.
For creative and consumer content the failure mode is flatness, not inaccuracy — and flatness passes an accuracy check. Terms here also carry technical constraints (reading speed, character budgets) that are part of the brief.
Angel Translation locks terms like this into a project terminology base before expert review begins, so the same source term resolves to the same target term across every document in a submission — and stays consistent in the next revision. See the 8-step AI + expert workflow.
Send us the files. Acknowledged in 4 hours, quoted in 24.
Request a Quote →Content Globalization solutions →