AWhat changed
Used a shared Transformer with different attention masks to train unidirectional, bidirectional and sequence-to-sequence language objectives, enabling both understanding and generation.
Scientific scope
Used a shared Transformer with different attention masks to train unidirectional, bidirectional and sequence-to-sequence language objectives, enabling both understanding and generation. Combines inherited Transformer and language-modeling objectives through a shared masking scheme. Original method only; later UniLM2/UniLMv2 or unrelated models in the umbrella repository are not included.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Combines inherited Transformer and language-modeling objectives through a shared masking scheme. Original method only; later UniLM2/UniLMv2 or unrelated models in the umbrella repository are not included.
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.
- Unified Language Model Pre-training for Natural Language Understanding and Generation
- Dong et al.: UniLM shared attention-mask language pretraining — official implementation
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