{"id":7500,"date":"2026-04-20T11:34:02","date_gmt":"2026-04-20T11:34:02","guid":{"rendered":"https:\/\/poeditor.com\/blog\/?p=7500"},"modified":"2026-04-20T11:34:03","modified_gmt":"2026-04-20T11:34:03","slug":"quality-estimation-scores","status":"publish","type":"post","link":"https:\/\/poeditor.com\/blog\/quality-estimation-scores\/","title":{"rendered":"What are Quality Estimation scores?"},"content":{"rendered":"\n
\"\"<\/figure>\n\n\n\n

When it comes to evaluating translations, we have all these scores, metrics, as well as human judgement to asses the quality. In this article, we’re going to be discussing Quality Estimation (QE) scores, which are gaining more and more importance today. They have one big advantage: there’s no need for a reference translation.<\/p>\n\n\n\n

What are Quality Estimation scores?<\/h2>\n\n\n\n

Quality Estimation scores are predictions of translation quality<\/a>. They are generated by machine learning models that analyze the source text and its translated output, and the neat part is that the QE systems don’t require a human-created reference translation <\/mark>to compare against.<\/p>\n\n\n\n

Here’s how they work: QE systems learn patterns from large datasets of translations that have been previously annotated for quality. It’s because of this training that they can estimate how accurate, fluent, or usable a new translation is likely to be.<\/p>\n\n\n\n

These scores can be produced at different levels of granularity. Some systems give sentence-level predictions, while others can assign scores to individual words or phrases. It’s thus possible to identify specific problem areas within a translation.<\/p>\n\n\n\n

Common quality categories<\/h2>\n\n\n\n

Raw QE scores are often continuous numerical values (0.0 to 1.0, for example), but companies often convert numerical QE outputs into categorical labels because they are easier to interpret and act upon. You’ll generally find these four categories:<\/p>\n\n\n\n