paper-with-me

Semantic entity labeling 벤치마크

Semantic entity labeling on FUNSD

15개 결과 · ⬇ CSV · JSON

F1

82.25 84.99 87.72 90.46 93.2 2020-12 2026-11 LayoutLMv2LARGE — 84.2 (2020-12-29) LayoutLMv2BASE — 82.76 (2020-12-29) LILT — 88.41 (2022-02-28) LayoutLMv3 Large — 92.08 (2022-04-18) Doc2Graph — 82.25 (2022-08-23) XDoc1M — 89.4 (2022-10-06) ERNIE-Layoutlarge — 93.12 (2022-10-12) StrucTexTv2 (large) — 91.82 (2023-03-01) StrucTexTv2 (small) — 89.23 (2023-03-01) GeoLayoutLM — 92.86 (2023-04-21) LayoutMask (large) — 93.2 (2023-05-30) LayoutMask (base) — 92.91 (2023-05-30) DocTr — 84.0 (2023-07-16) TPP (LayoutMask) — 85.16 (2023-10-17) RORE (GeoLayoutLM) — 91.84 (2024-09-29) LayoutLMv2LARGE — 84.2 (2020-12-29) LILT — 88.41 (2022-02-28) LayoutLMv3 Large — 92.08 (2022-04-18) ERNIE-Layoutlarge — 93.12 (2022-10-12) LayoutMask (large) — 93.2 (2023-05-30)
RankModel F1 PaperCodeYear
1 LayoutMask (large) 93.20 LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding 2023
2 ERNIE-Layoutlarge 93.12 ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding PaddlePaddle/PaddleNLP · NormXU/ERNIE-Layout-Pytorch 2022
3 LayoutMask (base) 92.91 LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding 2023
4 GeoLayoutLM 92.86 GeoLayoutLM: Geometric Pre-training for Visual Information Extraction alibabaresearch/advancedliteratemachinery 2023
5 LayoutLMv3 Large 92.08 LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking huggingface/transformers · microsoft/unilm · pwc-1/Paper-9 · +1 2022
6 RORE (GeoLayoutLM) 91.84 Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding chongzhangFDU/ROOR 2024
7 StrucTexTv2 (large) 91.82 StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training PaddlePaddle/VIMER 2023
8 XDoc1M 89.4 XDoc: Unified Pre-training for Cross-Format Document Understanding microsoft/unilm 2022
9 StrucTexTv2 (small) 89.23 StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training PaddlePaddle/VIMER 2023
10 LILT 88.41 LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding huggingface/transformers · jpwang/lilt · pwc-1/Paper-9 · +2 2022
11 TPP (LayoutMask) 85.16 Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction chongzhangfdu/tpp · WinterShiver/Token-Path-Prediction 2023
12 LayoutLMv2LARGE 84.2 LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding huggingface/transformers · PaddlePaddle/PaddleOCR · microsoft/unilm · +6 2020
13 DocTr 84 DocTr: Document Transformer for Structured Information Extraction in Documents 2023
14 LayoutLMv2BASE 82.76 LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding huggingface/transformers · PaddlePaddle/PaddleOCR · microsoft/unilm · +6 2020
15 Doc2Graph 82.25 Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks andreagemelli/doc2graph 2022
1–15 / 15 페이지당 10 20 50 100