Datasets › FUNSD

FUNSD (Form Understanding in Noisy Scanned Documents)

Introduced by Guillaume Jaume et al. in FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents archive 2025-07-28

Form Understanding in Noisy Scanned Documents (FUNSD) comprises 199 real, fully annotated, scanned forms. The documents are noisy and vary widely in appearance, making form understanding (FoUn) a challenging task. The proposed dataset can be used for various tasks, including text detection, optical character recognition, spatial layout analysis, and entity labeling/linking.

Source: FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents

Image source: https://guillaumejaume.github.io/FUNSD/

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 1 newer paper was judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Semantic entity labeling · FUNSD (1 judged, 0 placed), Relation Extraction · FUNSD (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

First row (archive order)PaperCode
Semantic entity labeling FUNSD LayoutMask (large) F1 93.20 LayoutMask: Enhance Text-Layout Interaction in... — 15 Compare
Relation Extraction FUNSD LayoutLMv3 large EM + BBO + RSF F1 90.81 A LayoutLMv3-Based Model for Enhanced Relation... — 9 Compare
Entity Linking FUNSD GeoLayoutLM F1 89.45 GeoLayoutLM: Geometric Pre-training for Visual... alibabaresearch/advancedliteratemachinery 7 Compare

Papers archive 2025-07-28

papers with a benchmark row: 17 · with a code link: 12 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (4 of 17 with a benchmark row: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 17 of 17 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 179. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding 1 3 29 Sep 2024 not harvested
A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents 0 1 16 Apr 2024 not harvested
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction 2 3 17 Oct 2023 not harvested
DocTr: Document Transformer for Structured Information Extraction in Documents 0 2 16 Jul 2023 not harvested
LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding 0 2 30 May 2023 not harvested
GeoLayoutLM: Geometric Pre-training for Visual Information Extraction 1 4 21 Apr 2023 not harvested
StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training 1 2 1 Mar 2023 not harvested
DGCN Based Solution for Entity Linking on Visual Rich Document 0 1 16 Nov 2022 not harvested
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding 2 1 12 Oct 2022 community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
XDoc: Unified Pre-training for Cross-Format Document Understanding 1 1 6 Oct 2022 not harvested
Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks 1 2 23 Aug 2022 not harvested
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking 4 2 18 Apr 2022 not harvested
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding 5 1 28 Feb 2022 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Entity Relation Extraction as Dependency Parsing in Visually Rich Documents 0 1 19 Oct 2021 not harvested
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents 2 1 10 Aug 2021 official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding 9 3 29 Dec 2020 not harvested
LayoutLM: Pre-training of Text and Layout for Document Image Understanding 19 1 31 Dec 2019 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)

Dataset loaders archive 2025-07-28

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Custom

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • FUNSD

1 variant name, as the archive lists them.

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