S$^2$SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers

TL;DR

This paper introduces S$^2$SQL, a syntax-injected graph encoder for text-to-SQL parsing that leverages question syntax and diverse relational embeddings, achieving state-of-the-art results on Spider.

Contribution

The paper proposes a novel syntax-injected question-schema graph encoder with a decoupling constraint, enhancing text-to-SQL performance beyond existing methods.

Findings

Outperforms all existing methods on Spider with pre-training.

Ranks first on the Spider leaderboard.

Improves robustness on Spider-Syn.

Abstract

The task of converting a natural language question into an executable SQL query, known as text-to-SQL, is an important branch of semantic parsing. The state-of-the-art graph-based encoder has been successfully used in this task but does not model the question syntax well. In this paper, we propose S$^2$SQL, injecting Syntax to question-Schema graph encoder for Text-to-SQL parsers, which effectively leverages the syntactic dependency information of questions in text-to-SQL to improve the performance. We also employ the decoupling constraint to induce diverse relational edge embedding, which further improves the network's performance. Experiments on the Spider and robustness setting Spider-Syn demonstrate that the proposed approach outperforms all existing methods when pre-training models are used, resulting in a performance ranks first on the Spider leaderboard.