Machine translation & AI quality — found from sitemap — Locize

Cited by

Facts read from this source

• Qe default availability Report an error

  “Availability: Enabled by default for new projects, opt-in for existing ones. Requires enabled machine/AI translation.”

• Qe scoring Report an error

  “Quality Estimation (QE) lets an AI evaluator score every AI-produced translation with a confidence estimate between 0 and 1, together with a short reason.”

• Qe scope Report an error

  “Only AI translations are scored at translation time (traditional machine translation is not).”

• Qe provider Report an error

  “Scoring uses the same AI provider that produced the translation: with your own API key (OpenAI, Gemini, Mistral AI, Anthropic) the scoring runs on your key; with the built-in Locize AI it consumes AI tokens like any other Locize AI usage.”

• Qe threshold Report an error

  “The needs-review threshold defaults to 0.7. A different threshold between 0 and 1 can currently not be stored for a project.”

• Qe review AI workflow Report an error

  “Low-confidence AI translations (score below the threshold, or with a major issue found) become pending reviews, even in languages that don't have review proposals enabled.”

• Qe critique categories Report an error

  “Routed proposals carry a critique: issue categories (accuracy, fluency, terminology, style) with severity and a short note. When the evaluator can clearly improve the translation, it also includes a suggested revision you can apply with one click.”

• Qe score removal Report an error

  “When an AI translation is edited by a human, re-translated, or replaced from translation memory, its confidence score is removed automatically.”

• Qe not mqm Report an error

  “QE does not produce span-level MQM error annotations, MQM scorecards, or certified MQM scores, and Locize does not claim MQM conformance.”

• Qe score doubling Report an error

  “Scoring roughly doubles the AI calls of a translation run. On very large namespaces the backend caps scoring per language and saves the remaining translations unscored.”

• Qe scores not published Report an error

  “Scores are editor metadata: they are not included in your published translation files.”

• Qe provenance export Report an error

  “Review decisions preserve the confidence score at decision time in the segment history; the provenance export (project overview, context menu of a version, language or namespace) packages this evidence as CSV and JSON for audits.”

• AI review feature Report an error

  “AI Review applies the same evaluator to existing translations of any origin and turns the doubted ones into review proposals with a suggested fix.”

• Qe EU AI act Report an error

  “Routing low-confidence AI translations into documented human review also supports the human-review exemption path of the EU AI Act's transparency rules: see Running an Article 50(4)-compatible review workflow (legal background in the explainer).”

• Qe complements checks Report an error

  “Quality Estimation complements the deterministic checks & issues, it does not replace them: broken placeholders or untranslated fragments are best caught by those checks.”

• Qe styleguide glossary Report an error

  “A Styleguide and Glossary improve the evaluator's judgement the same way they improve translations.”

Scores citing this record

• The App Developer Machine translation & AI quality
• The App Developer Translation memory, terminology & review workflow
• The Data Protection Officer Machine translation & AI quality
• The In-House Document Translator Machine translation & AI quality
• The In-House Document Translator Translation memory, terminology & review workflow
• The In-House Document Translator Data export, portability & self-hosting
• The E-Commerce Marketer Machine translation & AI quality
• The Localization Manager Machine translation & AI quality
• The Skeptic Machine translation & AI quality