Machine Translation Post-Editing (MTPE), Done Right

Post-edit to the right standard, light vs full per ISO 18587, spot the errors machines make, and price MTPE so it actually pays.

MTPE is now one of the largest categories of paid translation work, and the way it is usually priced quietly transfers all the benefit to the client. Master the ISO 18587 distinction between light and full post-editing, the error patterns MT and LLMs reliably produce, and an efficient pass that keeps you fast without going below the level. Then learn to estimate effort before you quote and price MTPE so the machine speed pays you, not just the client.

What you'll learn

• Apply the ISO 18587 light vs full post-editing distinction
• Choose the right post-editing level from the brief and risk
• Spot the error patterns MT and LLMs reliably produce
• Work faster without letting quality slip below the level
• Estimate post-editing effort before you quote
• Price MTPE by time and quality, not by the machine's discount

Course content

1. 1. What MTPE is, and why it is now most of the work (14 min)
2. 2. Light vs full: the ISO 18587 distinction (15 min)
3. 3. The error patterns machines make (15 min)
4. 4. The efficient post-edit pass (15 min)
5. 5. Estimating effort before you quote (15 min)
6. 6. Pricing MTPE so it pays (16 min)

Related courses

• AI for Translators: Your First LLM Workflow — Drive ChatGPT, Claude & Gemini as a translation copilot: a repeatable, confidentiality-safe workflow that keeps you the editor in charge.
• Prompt Engineering for Translators — Turn vague AI output into on-brief translations: glossaries, style rules, and reusable templates that make ChatGPT, Claude and Gemini obey.
• AI Quality Evaluation & Supervision — Supervise the machine, don't just translate: grade AI output with MQM, use quality estimation, and design review workflows that scale.