RATSQL + GAP

Reported on 3 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Natural Language Processing3 results

Semantic Parsingonspider
Accuracy· 2020-12-18
69.7
best: 84.1 (RESDSQL-3B + NatSQL)
SOTA
Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training arXiv:2012.10309
Semantic Parsingonspider
Exact Match Accuracy (Dev)· 2020-12-18
71.8
best: 81.6 (datagpt-sql-7B + InvalidSQL-Feedback)
SOTA
Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training arXiv:2012.10309
Text-To-SQLonspider
Exact Match Accuracy (Dev)· 2020-12-18
71.8
best: 81.6 (datagpt-sql-7B + InvalidSQL-Feedback)
SOTA
Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training arXiv:2012.10309