HyperAIHyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Key Information Extraction On Cord

평가 지표

F1

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
F1
Paper TitleRepository
LILT96.07LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding-
LayoutLMv2BASE94.95LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding-
LayoutMask (base)96.99LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding-
RORE (GeoLayoutLM)98.52Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding-
TPP (LayoutMask)96.92Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction-
GeoLayoutLM97.97GeoLayoutLM: Geometric Pre-training for Visual Information Extraction-
LayoutLMv3 Large97.46LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking-
LayoutMask (large)97.19LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding-
LayoutLMv2LARGE96.01LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding-
0 of 9 row(s) selected.
Key Information Extraction On Cord | SOTA | HyperAI초신경