Mention Extraction and Linking for SQL Query Generation

TL;DR

This paper introduces a unified extraction-linking approach for text-to-SQL conversion that simplifies the process and captures inter-dependencies, achieving top performance on the WikiSQL benchmark.

Contribution

A novel extraction-linking method that unifies slot recognition and schema linking, improving over modular slot-filling systems in text-to-SQL tasks.

Findings

Achieved first place on the WikiSQL benchmark

Outperformed modular slot-filling systems

Effectively captures inter-dependencies among SQL clauses

Abstract

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.