Semantic Decomposition of Question and SQL for Text-to-SQL Parsing

TL;DR

This paper introduces QPL, a modular language for decomposing complex SQL queries into simpler sub-queries, improving text-to-SQL parsing, especially for cross-domain and complex queries, by augmenting datasets and enabling question decomposition.

Contribution

The paper proposes a new Query Plan Language (QPL) for systematic SQL decomposition, along with a translation method and dataset augmentation, enhancing semantic parsing and interpretability.

Findings

QPL improves parsing accuracy on complex queries

Training with QPL yields more effective question decomposers

QPL-based methods are more interpretable and schema-sensitive

Abstract

Text-to-SQL semantic parsing faces challenges in generalizing to cross-domain and complex queries. Recent research has employed a question decomposition strategy to enhance the parsing of complex SQL queries. However, this strategy encounters two major obstacles: (1) existing datasets lack question decomposition; (2) due to the syntactic complexity of SQL, most complex queries cannot be disentangled into sub-queries that can be readily recomposed. To address these challenges, we propose a new modular Query Plan Language (QPL) that systematically decomposes SQL queries into simple and regular sub-queries. We develop a translator from SQL to QPL by leveraging analysis of SQL server query optimization plans, and we augment the Spider dataset with QPL programs. Experimental results demonstrate that the modular nature of QPL benefits existing semantic-parsing architectures, and training text-to-QPL parsers is more effective than text-to-SQL parsing for semantically equivalent queries. The QPL approach offers two additional advantages: (1) QPL programs can be paraphrased as simple questions, which allows us to create a dataset of (complex question, decomposed questions). Training on this dataset, we obtain a Question Decomposer for data retrieval that is sensitive to database schemas. (2) QPL is more accessible to non-experts for complex queries, leading to more interpretable output from the semantic parser.