Text-to-SQL on WikiSQL Fully-supervised (dev)
91.4Execution AccuracyGuo & Gao w. GRAPPA (MLM)
Evaluation Results
| Method | Links | |
|---|---|---|
| Guo & Gao w. GRAPPA (MLM)Execution-guided decoding=false, Backbone=GRAPPA, Pre-training Objective=MLM2020.09 | 91.4 | |
| Guo & Gao w. RoBERTa-largeExecution-guided decoding=false, Backbone=RoBERTa-large2020.09 | 91.2 | |
| Guo & Gao w. GRAPPA (SSP)Execution-guided decoding=false, Backbone=GRAPPA, Pre-training Objective=SSP2020.09 | 91.2 | |
| Guo & Gao w. GRAPPA (MLM+SSP)Execution-guided decoding=false, Backbone=GRAPPA, Pre-training Objective=MLM+SSP2020.09 | 91.2 | |
| Guo & GaoExecution-guided decoding=false2020.09 | 90.3 | |
| He et al.Execution-guided decoding=false2020.09 | 89.5 | |
| Lyu et al.Execution-guided decoding=false2020.09 | 89.1 | |
| Hwang et al.Execution-guided decoding=false2020.09 | 87.2 | |
| Shi et al.Execution-guided decoding=false2020.09 | 84 | |
| Guo & Gao w. GRAPPA (MLM+SSP) (10k)Execution-guided decoding=false, Backbone=GRAPPA, Pre-training Objective=MLM+SSP, Training Data Scale=10k2020.09 | 82.3 | |
| Guo & Gao w. RoBERTa-large (10k)Execution-guided decoding=false, Backbone=RoBERTa-large, Training Data Scale=10k2020.09 | 79.6 | |
| Dong & LapataExecution-guided decoding=false2020.09 | 79 |