TAPEX-Large

Reported on 5 benchmarks across 2 tasks · 1 paper · 5 SOTA

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

Natural Language Processing5 results

Semantic ParsingonSQA
Denotation Accuracy· 2021-07-16
74.5
SOTA
TAPEX: Table Pre-training via Learning a Neural SQL Executor arXiv:2107.07653
Semantic ParsingonWikiTableQuestions
Accuracy (Dev)· 2021-07-16
57
best: 65 (Binder)
SOTA
TAPEX: Table Pre-training via Learning a Neural SQL Executor arXiv:2107.07653
Semantic ParsingonWikiTableQuestions
Accuracy (Test)· 2021-07-16
57.5
best: 80.8 (ARTEMIS-DA)
SOTA
TAPEX: Table Pre-training via Learning a Neural SQL Executor arXiv:2107.07653
Table-based Fact VerificationonTabFact
Test· 2021-07-16
84.2
best: 93.1 (ARTEMIS-DA)
SOTA
TAPEX: Table Pre-training via Learning a Neural SQL Executor arXiv:2107.07653
Table-based Fact VerificationonTabFact
Val· 2021-07-16
84.6
best: 89.2 (PASTA)
SOTA
TAPEX: Table Pre-training via Learning a Neural SQL Executor arXiv:2107.07653