Entity Linking On Funsd

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	F1	Paper Title	Repository
SINGU_GROUP	70.51	DGCN Based Solution for Entity Linking on Visual Rich Document	-
RORE (GeoLayoutLM)	88.46	Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
GeoLayoutLM	89.45	GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
TPP (LayoutMask)	79.20	Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction	-
SERA	65.96	Entity Relation Extraction as Dependency Parsing in Visually Rich Documents	-
Doc2Graph	53.36	Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
DocTr	73.9	DocTr: Document Transformer for Structured Information Extraction in Documents	-

0 of 7 row(s) selected.