Key Information Extraction On Sroie
評価指標
F1
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 |
|---|---|---|---|
| LayoutLMv2LARGE | 96.61 | LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding | - |
| RORE (GeoLayoutLM) | 96.97 | Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding | - |
| LayoutLMv2LARGE (Excluding OCR mismatch) | 97.81 | LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding | - |
| LayoutLMv2BASE | 96.25 | LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding | - |
| ChatGPT 3.5 SpatialFormat | - | LAPDoc: Layout-Aware Prompting for Documents | - |
0 of 5 row(s) selected.