Semantic Entity Recognition on FUNSD
93.62EN ScoreWukong-Reader
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Wukong-Reader#Params=470M2024.09 | 93.62 | — | |
| Bi-VLDoc#Params=409M2024.09 | 93.44 | — | |
| LayoutMask#Params=404M2024.09 | 93.2 | — | |
| ERNIE-Layout#Params=large2024.09 | 93.12 | — | |
| RORE-LayoutLMv3#Params=368M+242024.09 | 92.14 | — | |
| RORE-GeoLayoutLM#Params=399M+242024.09 | 91.84 | — | |
| LayoutLMv3#Params=368M, reproduced=true2024.09 | 91.7 | — | |
| RORE-LayoutLMv3#Params=133M+122024.09 | 91.39 | — | |
| ESP#Params=50M, supervised_pretrained=true2024.09 | 91.12 | — | |
| GeoLayoutLM#Params=399M2024.09 | 91.1 | — | |
| LAGaBi#Params=133M2024.09 | 91 | — | |
| LayoutLMv3#Params=133M2024.09 | 90.85 | — | |
| DocGraphLM#Params=base2024.09 | 88.77 | — | |
| LiLT#Params=base2024.09 | 88.41 | — | |
| GraphDoc#Params=265M2024.09 | 87.77 | — | |
| mmLayout#Params=large2024.09 | 86.49 | — | |
| LiLT[InfoXLM] BASEMultitask fine-tuning=true, Pre-training Docs Language=English only, Pre-training Docs Size=11M2022.02 | 85.74 | — | |
| FormNet#Params=large2024.09 | 84.69 | — | |
| DocFormer#Params=502M2024.09 | 84.55 | — | |
| BROS#Params=340M2024.09 | 84.52 | — | |
| LiLT[InfoXLM]-BASEPre-training Data Language=English only, Pre-training Docs Size=11M, Evaluation Protocol=fine-tuning on X, testing on X2022.02 | 84.15 | — | |
| DocTr#Params=153M2024.09 | 84 | — | |
| StrucTexT#Params=107M2024.09 | 83.09 | — | |
| MatchVIE#Params=base2024.09 | 81.33 | — | |
| LayoutXLM-BASEPre-training Data Language=Multilingual, Pre-training Docs Size=30M, Evaluation Protocol=fine-tuning on X, testing on X2022.02 | 79.4 | — | |
| LayoutXLM_BASEMultitask fine-tuning=true, Pre-training Docs Language=Multilingual, Pre-training Docs Size=30M2022.02 | 79.24 | — | |
| SPADE#Params=base2024.09 | 72 | — | |
| InfoXLM-BASEPre-training Data Language=-, Pre-training Docs Size=-, Evaluation Protocol=fine-tuning on X, testing on X2022.02 | 68.52 | — | |
| XLM-RoBERTa-BASEPre-training Data Language=-, Pre-training Docs Size=-, Evaluation Protocol=fine-tuning on X, testing on X2022.02 | 66.7 | — | |
| XLM-R_BASEMultitask fine-tuning=true2022.02 | 66.33 | — | |
| InfoXLM_BASEMultitask fine-tuning=true2022.02 | 65.38 | — | |
| BERTModality=Language, Model size=BASE2022.03 | — | 60.26 | |
| BERT_LARGE#Params=340M2023.04 | — | 65.63 | |
| BROSModality=Language, Model size=BASE2022.03 | — | 81.21 | |
| BROS_LARGE#Params=340M2023.04 | — | 84.52 | |
| DocFormerModality=Language + Layout + Vision, Model size=BASE2022.03 | — | 83.34 | |
| GeoLayoutLM#Params=399M2023.04 | — | 92.86 | |
| HGALayoutLM_LARGEParams=307.7M, Flops=218.95G2024.07 | — | 95.3 | |
| InfoXLM_BASEEvaluation Protocol=Cross-lingual zero-shot transfer2022.02 | — | 68.52 | |
| LayoutLLMParams=6914.38M, Flops=8654.62G2024.07 | — | 95.3 | |
| LayoutLM_LARGE#Params=343M2023.04 | — | 78.95 | |
| LayoutLMv1Modality=Language + Layout + Vision, Model size=BASE2022.03 | — | 79.27 | |
| LayoutLMv2_LARGE#Params=426M2023.04 | — | 84.2 | |
| LayoutLMv3_LARGE#Params=357M2023.04 | — | 92.08 | |
| LayoutXLMModality=Language + Layout + Vision, Model size=BASE2022.03 | — | 82.76 | |
| LayoutXLM_BASEPre-training Docs Language=Multilingual, Pre-training Docs Size=30M, Evaluation Protocol=Cross-lingual zero-shot transfer2022.02 | — | 79.4 | |
| LiLT [InfoXLM] BASEPre-training Docs Language=English only, Pre-training Docs Size=11M, Evaluation Protocol=Cross-lingual zero-shot transfer2022.02 | — | 84.15 | |
| RoBERTaModality=Language, Model size=BASE2022.03 | — | 66.48 | |
| SelfDocModality=Language + Layout + Vision, Model size=BASE2022.03 | — | 83.36 | |
| StrucTexT#Params=107M2023.04 | — | 83.09 | |
| StructuralLMModality=Language + Layout, Model size=LARGE2022.03 | — | 85.14 | |
| XLM-R_BASEEvaluation Protocol=Cross-lingual zero-shot transfer2022.02 | — | 66.7 | |
| XYLayoutLMModality=Language + Layout + Vision, Model size=BASE2022.03 | — | 83.35 |