X-SQL: reinforce schema representation with context

TL;DR

X-SQL introduces a novel network architecture that enhances schema representation for NL-to-SQL parsing by integrating contextual embeddings from BERT-style models and type information, achieving state-of-the-art results on WikiSQL.

Contribution

The paper presents X-SQL, a new architecture that improves schema representation by combining contextual BERT embeddings with type info for better NL-to-SQL parsing.

Findings

Achieved state-of-the-art performance on WikiSQL dataset.

Enhanced schema representation improves parsing accuracy.

Demonstrated effectiveness of contextual embeddings in schema modeling.

Abstract

In this work, we present X-SQL, a new network architecture for the problem of parsing natural language to SQL query. X-SQL proposes to enhance the structural schema representation with the contextual output from BERT-style pre-training model, and together with type information to learn a new schema representation for down-stream tasks. We evaluated X-SQL on the WikiSQL dataset and show its new state-of-the-art performance.