List your company
ResearchFormerly WizWand

Entity Recognition on CORD official (test)

98.94F1 ScoreUDoc
89.309691.809894.3196.8102Apr 18, 2022Jul 2, 2022Sep 16, 2022Dec 1, 2022Feb 14, 2023May 1, 2023Jul 16, 2023
Updated 8mo ago

Evaluation results

MethodLinks
UDocParameters=272M, Modality=T+L+I (R), Image Embedding=ResNet-50, Not_Directly_Comparable=true2022.0498.94
DocTr#params=153M2023.0798.2
LayoutLMv3_LARGEParameters=368M, Modality=T+L+I (P), Image Embedding=Linear2022.0497.46
BROS_LARGEParameters=340M, Modality=T+L, Image Embedding=None2022.0497.4
BROS_LARGE#params=340M2023.0797.3
FormNet#params=345M2023.0797.3
FormNetParameters=345M, Modality=T+L, Image Embedding=None2022.0497.28
DocFormer_LARGE#params=536M2023.0797
DocFormer_LARGEParameters=536M, Modality=T+L+I (G), Image Embedding=ResNet-502022.0496.99
UDoc*Pretraining Source=IIT-CDIP, Pretraining #Data=1M, Pretraining Scale=Region, Pretraining Max #Words=64x512, Pretraining Modality=V+L, #Param.=272M2022.0496.86
UDocPretraining Source=IIT-CDIP, Pretraining #Data=1M, Pretraining Scale=Region, Pretraining Max #Words=64x512, Pretraining Modality=V+L, #Param.=272M2022.0496.64
LayoutLMv3_BASEParameters=133M, Modality=T+L+I (P), Image Embedding=Linear2022.0496.56
BROS_BASE#params=110M2023.0796.5
TILT-LargePretraining Source=RVL-CDIP+, Pretraining #Data=1.1M, Pretraining Scale=Word, Pretraining Max #Words=512, Pretraining Modality=V+L, #Param.=780M2022.0496.33
DocFormer_BASEParameters=183M, Modality=T+L+I (G), Image Embedding=ResNet-502022.0496.33
TILT_LARGEParameters=780M, Modality=T+L+I (R), Image Embedding=U-Net2022.0496.33
DocFormer_BASE#params=183M2023.0796.3
LiLT_BASEModality=T+L, Image Embedding=None2022.0496.07
LayoutLMv2-LargePretraining Source=IIT-CDIP, Pretraining #Data=11M, Pretraining Scale=Word, Pretraining Max #Words=512, Pretraining Modality=V+L, #Param.=426M2022.0496.01
LayoutLMv2_LARGEParameters=426M, Modality=T+L+I (G), Image Embedding=ResNeXt101-FPN2022.0496.01
LayoutLMv2_LARGE#params=426M2023.0796
BROS_BASEParameters=110M, Modality=T+L, Image Embedding=None2022.0495.73
TILT-BasePretraining Source=RVL-CDIP+, Pretraining #Data=1.1M, Pretraining Scale=Word, Pretraining Max #Words=512, Pretraining Modality=V+L, #Param.=230M2022.0495.11
TILT_BASEParameters=230M, Modality=T+L+I (R), Image Embedding=U-Net2022.0495.11
LayoutLMv2_BASE#params=200M2023.0795
LayoutLM_LARGE#params=343M2023.0795
LayoutLMv2-BasePretraining Source=IIT-CDIP, Pretraining #Data=11M, Pretraining Scale=Word, Pretraining Max #Words=512, Pretraining Modality=V+L, #Param.=200M2022.0494.95
LayoutLMv2_BASEParameters=200M, Modality=T+L+I (G), Image Embedding=ResNeXt101-FPN2022.0494.95
LayoutLM-LargePretraining Source=IIT-CDIP, Pretraining #Data=11M, Pretraining Scale=Word, Pretraining Max #Words=512, Pretraining Modality=L, #Param.=343M2022.0494.93
LayoutLM-BasePretraining Source=IIT-CDIP, Pretraining #Data=11M, Pretraining Scale=Word, Pretraining Max #Words=512, Pretraining Modality=L, #Param.=113M2022.0494.72
LayoutLM_BASE#params=113M2023.0794.7
RoBERTa_LARGEParameters=355M, Modality=T, Image Embedding=None2022.0493.8
RoBERTa_BASEParameters=125M, Modality=T, Image Embedding=None2022.0493.54
BERT-LargePretraining Scale=Word, Pretraining Max #Words=512, Pretraining Modality=L, #Param.=340M2022.0490.25
BERT_LARGEParameters=340M, Modality=T, Image Embedding=None2022.0490.25
BERT-BasePretraining Scale=Word, Pretraining Max #Words=512, Pretraining Modality=L, #Param.=110M2022.0489.68
BERT_BASEParameters=110M, Modality=T, Image Embedding=None2022.0489.68