Mention Extraction and Linking for SQL Query Generation
This work provides a simplified and more effective approach for generating SQL queries from natural language for developers working with databases.
This paper proposes a unified extraction-linking approach for text-to-SQL query generation, moving away from modularized slot-filling systems. The method achieves first place on the WikiSQL benchmark.
On the WikiSQL benchmark, state-of-the-art text-to-SQL systems typically take a slot-filling approach by building several dedicated models for each type of slots. Such modularized systems are not only complex butalso of limited capacity for capturing inter-dependencies among SQL clauses. To solve these problems, this paper proposes a novel extraction-linking approach, where a unified extractor recognizes all types of slot mentions appearing in the question sentence before a linker maps the recognized columns to the table schema to generate executable SQL queries. Trained with automatically generated annotations, the proposed method achieves the first place on the WikiSQL benchmark.