AWhat changed
Pretrained a complete shared encoder–decoder on corrupted multilingual text using span masking and sentence permutation, then adapted the initialization to supervised and unsupervised translation.
Scientific scope
Pretrained a complete shared encoder–decoder on corrupted multilingual text using span masking and sentence permutation, then adapted the initialization to supervised and unsupervised translation. Inherits BART's denoising and Transformer architecture. The contribution is multilingual full-sequence pretraining and transfer study, not invention of denoising or translation. Gains are data-resource and language-pair dependent; original25-language model is not later expanded releases.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits BART's denoising and Transformer architecture. The contribution is multilingual full-sequence pretraining and transfer study, not invention of denoising or translation. Gains are data-resource and language-pair dependent; original25-language model is not later expanded releases.
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.
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