AWhat changed
Combined low-resource language data mining and sparsely gated translation models with FLORES-200 evaluation across a large set of language directions.
Scientific scope
Combined low-resource language data mining and sparsely gated translation models with FLORES-200 evaluation across a large set of language directions. Integrated translation-and-evaluation package, not an invention of mixture-of-experts. Translation quality and toxicity metrics are benchmark-specific, not equal quality across every language.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Integrated translation-and-evaluation package, not an invention of mixture-of-experts. Translation quality and toxicity metrics are benchmark-specific, not equal quality across every language.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- No Language Left Behind: Scaling Human-Centered Machine Translation
- NLLB Team and colleagues: 200-language translation and FLORES-200 evaluation — official research record
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction