Xu et al.: LayoutLM joint text-layout document pretraining

What changed

Combined text representations with two-dimensional document layout and visual information in a pretrained model for scanned-document understanding.

Scientific scope

Combined text representations with two-dimensional document layout and visual information in a pretrained model for scanned-document understanding. Year denotes December 2019 preprint; conference publication followed in 2020. Builds on language/vision pretraining; no unqualified first-ever claim or guarantee of error-free document extraction is imported.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Year denotes December 2019 preprint; conference publication followed in 2020. Builds on language/vision pretraining; no unqualified first-ever claim or guarantee of error-free document extraction is imported.

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.

• LayoutLM: Pre-training of Text and Layout for Document Image Understanding
• Xu et al.: LayoutLM joint text-layout document 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