HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Semantic Entity Labeling On Funsd

평가 지표

F1

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
F1
Paper TitleRepository
LayoutLMv2LARGE84.2LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
StrucTexTv2 (large)91.82StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
Doc2Graph82.25Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
XDoc1M89.4XDoc: Unified Pre-training for Cross-Format Document Understanding
LILT88.41LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
LayoutLMv3 Large92.08LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
RORE (GeoLayoutLM)91.84Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
TPP (LayoutMask)85.16Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction-
DocTr84DocTr: Document Transformer for Structured Information Extraction in Documents-
ERNIE-Layoutlarge93.12ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
LayoutLMv2BASE82.76LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
LayoutMask (large)93.20LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding-
GeoLayoutLM92.86GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
LayoutMask (base)92.91LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding-
StrucTexTv2 (small)89.23StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
0 of 15 row(s) selected.