BWhat changed
Kept a learned BPE merge table while randomly suppressing candidate merges during training segmentation, exposing the translation model to multiple segmentations before deterministic inference.
Scientific scope
Kept a learned BPE merge table while randomly suppressing candidate merges during training segmentation, exposing the translation model to multiple segmentations before deterministic inference. Does not introduce a new BPE vocabulary or establish universal robustness. Dropout acts on merge operations, not neural activations. It inherits subword regularization's motivation and uses standard BPE when the dropout probability is zero.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Does not introduce a new BPE vocabulary or establish universal robustness. Dropout acts on merge operations, not neural activations. It inherits subword regularization's motivation and uses standard BPE when the dropout probability is zero.
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