HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Key Value Pair Extraction On Rfund En

평가 지표

key-value pair F1

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
key-value pair F1
Paper TitleRepository
LiLT ([InfoXLM]_base)52.18LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
PEneo (LayoutLMv2_base)71.97PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction
PEneo (LayoutLMv3_base)79.27PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction
LayoutLMv357.66LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
TPP (LayoutLMv3_base)50.27Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction-
PEneo (LiLT[EN-R]_base)74.22PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction
LayoutLMv2_base49.06LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
LayoutXLM_base53.98LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
PEneo (LiLT[InfoXLM]_base)74.29PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction
PEneo (LayoutXLM_base)74.25PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction
GeoLayoutLM69.03GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
Donut24.54OCR-free Document Understanding Transformer
LiLT ([EN-R]_base)54.33LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
0 of 13 row(s) selected.