ReasTAP-Large

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Semantic ParsingonWikiTableQuestions
Accuracy (Dev)· 2022-10-22
59.7
best: 65 (Binder)
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples arXiv:2210.12374
Semantic ParsingonWikiTableQuestions
Accuracy (Test)· 2022-10-22
58.7
best: 80.8 (ARTEMIS-DA)
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples arXiv:2210.12374
Table-based Fact VerificationonTabFact
Test· 2022-10-22
84.9
best: 93.1 (ARTEMIS-DA)
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples arXiv:2210.12374
Table-based Fact VerificationonTabFact
Val· 2022-10-22
84.6
best: 89.2 (PASTA)
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples arXiv:2210.12374