SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing

Open paper
Benchmark Model Rank Results
dialogue-state-tracking-on-cosqlRAT-SQL + SCoRe–question match accuracy: 51.6interaction match accuracy: 21.2
text-to-sql-on-sparcRAT-SQL + SCoRe–interaction match accuracy: 38.1question match accuracy: 62.4

Rank counts only results with a code link.