Papers › ERNIE-Layout: Layout-Knowledge Enhanced Multi-modal Pre-training for Document Understanding

ERNIE-Layout: Layout-Knowledge Enhanced Multi-modal Pre-training for Document Understanding

16 Jan 2022ACL ARR January 2022 1archive 2025-07-28

Anonymous

We propose ERNIE-Layout, a knowledge enhanced pre-training approach for visual document understanding, which incorporates layout-knowledge into the pre-training of visual document understanding to learn a better joint multi-modal representation of text, layout and image. Previous works directly model serialized tokens from documents according to a raster-scan order, neglecting the importance of the reading order of documents, leading to sub-optimal performance. We incorporate layout-knowledge from Document-Parser into document pre-training, which is used to rearrange the tokens following an order more consistent with human reading habits. And we propose the Reading Order Prediction (ROP) task to enhance the interactions within segments and correlation between segments and a fine-grained cross-modal alignment pre-training task named Replaced Regions Prediction (RRP). ERNIE-Layout attempts to fuse textual and visual features in a unified Transformer model, which is based on our newly proposed spatial-aware disentangled attention mechanism. ERNIE-Layout achieves superior performance on various document understanding tasks, setting new SOTA for four tasks, including information extraction, document classification, document question answering.

Paper PDF Code

Code

PaddlePaddle/PaddleNLP officialpaddle report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Document Classification Question Answering cross-modal alignment document understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections