TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data

Open paper
Benchmark Model Rank Results
text-to-sql-on-spiderMAPO + TABERTLarge (K = 3)#17Exact Match Accuracy (Dev): 64.5
semantic-parsing-on-wikitablequestionsMAPO + TABERTLarge (K = 3)#20Accuracy (Test): 51.8Accuracy (Dev): 52.2

Rank counts only results with a code link.