Quality estimation › FAQ › Can quality estimation score human translation, or only machine translation?
Yes.
Quality estimation for newly machine translated segments is the most exciting use case, because it is the most expensive and the most scalable.
In practice, production AI systems like ModelFront are also used for millions of human translations that traditionally had required additional manual work.
For example, in many workflows, human post-edited translations go to an additional review step, and translation memory matches exact matches still get a human look.
← Learn more about quality estimation
© 2026 qualityestimation.org
Supported by the team at ModelFront — AI to check and fix AI translations, and trigger human intervention where needed