List your company
ResearchFormerly WizWand

Table Fact Verification on TABFACT simple (test)

96.7AccuracyPASTA
49.17261.51173.8586.189Oct 1, 2020Feb 5, 2021Jun 13, 2021Oct 18, 2021Feb 23, 2022Jun 30, 2022Nov 5, 2022
Updated 8mo ago

Evaluation results

MethodLinks
PASTA2022.1196.7
REASTAP2022.1094.1
TAPEXpre-training_steps=50000, fine-tuning_steps=200002021.0793.9
Tapex2022.1193.9
TAPEX2022.1093.7
DecompTaPas2022.1093.6
SaMoE2022.1193.6
TableFormer2022.1093.3
DeBERTaV32022.1192.8
TAPASModel=Large, Pre-training Objective=Counterfactual + Synthetic2020.1092.3
Eisenschlos et al.model_category=Pre-trained Language Models2021.0792.3
TaPas2022.1092.3
Tapas2022.1192.3
BART2021.0790.7
BART2022.1090.6
TAPASModel=Base, Pre-training Objective=Counterfactual + Synthetic2020.1090.5
TAPASModel=Base, Pre-training Objective=Synthetic2020.1089.7
Schlichtkrull et al.Retrieval=Oracle2022.1188.9
Yang et al.model_category=Pre-trained Language Models2021.0788.3
ProgVGAT2022.1188.3
TAPASModel=Base, Pre-training Objective=Counterfactual2020.1087.8
TAPASModel=Base, Pre-training Objective=SQA2020.1087.2
Shi et al.model_category=Pre-trained Language Models2021.0785.9
HeterTFV2022.1085.9
LOGICALFACTCHECKER (program from LPA)2020.1085.5
Zhang et al.model_category=Pre-trained Language Models2021.0785.5
SAT2022.1085.5
SAT2022.1185.5
LOGICALFACTCHECKER (program from Seq2Action)2020.1085.4
Zhong et al.model_category=Pre-trained Language Models2021.0785.4
LFC2022.1085.4
LogicFactChecker2022.1185.4
TAPASModel=Base, Pre-training Objective=MASK-LM2020.1082
TABLE-BERT-Horizontal-T+F-Template2020.1079.1
Chen et al.model_category=Pre-trained Language Models2021.0779.1
Table-BERT2022.1179.1
LPA-Ranking w/ Discriminator (Caption)2020.1078.7
LPA-Ranking2022.1078.7
BERT classifier w/o Table2020.1051