TAPAS: Weakly Supervised Table Parsing via Pre-training
Open paper
Benchmark
Model
Rank
Results
semantic-parsing-on-wikisql
TAPAS-Large (weak supervision)
#5
Denotation accuracy (test): 83.6
semantic-parsing-on-wikitablequestions
TAPAS-Large (pre-trained on SQA)
#23
Accuracy (Test): 48.8
Accuracy (Dev): /
Rank counts only results with a code link.