Grounded Adaptation for Zero-shot Executable Semantic Parsing
Open paper
Benchmark
Model
Rank
Results
text-to-sql-on-sparc
GAZP + BERT
#4
interaction match accuracy: 23.5
question match accuracy: 45.9
dialogue-state-tracking-on-cosql
GAZP+BERT
#5
question match accuracy: 39.7
interaction match accuracy: 12.8
Rank counts only results with a code link.