Papers › ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding

ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding

12 Oct 2022arXiv:2210.06155archive 2025-07-28

Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Teng Hu, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding. However, most existing methods lack the systematic mining and utilization of layout-centered knowledge, leading to sub-optimal performances. In this paper, we propose ERNIE-Layout, a novel document pre-training solution with layout knowledge enhancement in the whole workflow, to learn better representations that combine the features from text, layout, and image. Specifically, we first rearrange input sequences in the serialization stage, and then present a correlative pre-training task, reading order prediction, to learn the proper reading order of documents. To improve the layout awareness of the model, we integrate a spatial-aware disentangled attention into the multi-modal transformer and a replaced regions prediction task into the pre-training phase. Experimental results show that ERNIE-Layout achieves superior performance on various downstream tasks, setting new state-of-the-art on key information extraction, document image classification, and document question answering datasets. The code and models are publicly available at http://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-layout.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2210.06155")

Code

Syntology Ran 2 of 7 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 7 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

NormXU/ERNIE-Layout-Pytorch mentioned on GitHubpytorchMIT 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

7 samples harvested; 2 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
1ran · fixture could not drive it
5unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from NormXU/ERNIE-Layout-Pytorch. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

exists NormXU/ERNIE-Layout-Pytorch/networks/modeling_erine_layout_extrapolation.py community (archive-listed) ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
pad_at_dim NormXU/ERNIE-Layout-Pytorch/networks/modeling_erine_layout_extrapolation.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · e62e48a00ed06f63 · report
ResNet101 NormXU/ERNIE-Layout-Pytorch/networks/visual_backbone.py community (archive-listed) unverified MIT (permissive) · 015a941d044dac12 · report
ResNet152 NormXU/ERNIE-Layout-Pytorch/networks/visual_backbone.py community (archive-listed) unverified MIT (permissive) · 8d726fd8fa82d461 · report
ResNet50 NormXU/ERNIE-Layout-Pytorch/networks/visual_backbone.py community (archive-listed) unverified MIT (permissive) · 363d1ff55bddc72b · report
drop_path NormXU/ERNIE-Layout-Pytorch/networks/modeling_erine_layout_extrapolation.py community (archive-listed) unverified MIT (permissive) · d4c1c406c2087434 · report
relative_position_bucket NormXU/ERNIE-Layout-Pytorch/networks/modeling_erine_layout.py community (archive-listed) unverified MIT (permissive) · bca8304ee996b24d · report

Tasks

Document Image ClassificationImage ClassificationKey Information ExtractionQuestion AnsweringSemantic entity labelingVisual Question AnsweringVisual Question Answering (VQA)document understandingdocument-image-classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic entity labeling FUNSD ERNIE-Layoutlarge F1 93.12 #2 of 15 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test ERNIE-Layout large (ensemble) ANLS 0.8841 #8 of 33 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test ERNIE-Layout large ANLS 0.8486 #16 of 33 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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