RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases

Text-to-SQL is the problem of converting a user question into an SQL query, when the question and database are given. In this paper, we present a neural network approach called RYANSQL (Recursively Yielding Annotation Network for SQL) to solve complex Text-to-SQL tasks for cross-domain databases. State-ment Position Code (SPC) is defined to trans-form a nested SQL query into a set of non-nested SELECT statements; a sketch-based slot filling approach is proposed to synthesize each SELECT statement for its corresponding SPC. Additionally, two input manipulation methods are presented to improve generation performance further. RYANSQL achieved 58.2% accuracy on the challenging Spider benchmark, which is a 3.2%p improvement over previous state-of-the-art approaches. At the time of writing, RYANSQL achieves the first position on the Spider leaderboard.

PDF Abstract CL (ACL) 2021 PDF CL (ACL) 2021 Abstract

Results from the Paper

Ranked #7 on Text-To-SQL on spider (Exact Match Accuracy (Test) metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text-To-SQL spider RYANSQL (BERT) Exact Match Accuracy (Dev) 66.6 # 9
Exact Match Accuracy (Test) 58.2 # 7