PSM-SQL: Progressive Schema Learning with Multi-granularity Semantics for Text-to-SQL

2025-02-07

AI Summary

In text-to-SQL translation, database schema redundancy hinders semantic learning, a deep semantic gap persists between natural language and SQL, and existing schema linking methods are limited to single-pass, table-level matching—ignoring multi-granularity interactions and cyclic dependencies. To address these challenges, we propose a progressive multi-granularity schema learning framework. Our approach introduces a novel chained iterative pruning strategy: (1) column-level embedding optimization via triplet loss; (2) joint classification and similarity modeling at the table level; and (3) database-level global reasoning through fine-tuning large language models. By enabling multi-granularity collaborative filtering and iterative refinement, the framework significantly improves schema-semantic alignment accuracy. Evaluated on mainstream text-to-SQL benchmarks, our method achieves 1–3 percentage points higher execution accuracy over state-of-the-art approaches, demonstrating both effectiveness and strong generalization across diverse schemas.

Technology Category

• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Machine Learning: Statistical Relational/Logic Learning
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

It is challenging to convert natural language (NL) questions into executable structured query language (SQL) queries for text-to-SQL tasks due to the vast number of database schemas with redundancy, which interferes with semantic learning, and the domain shift between NL and SQL. Existing works for schema linking focus on the table level and perform it once, ignoring the multi-granularity semantics and chainable cyclicity of schemas. In this paper, we propose a progressive schema linking with multi-granularity semantics (PSM-SQL) framework to reduce the redundant database schemas for text-to-SQL. Using the multi-granularity schema linking (MSL) module, PSM-SQL learns the schema semantics at the column, table, and database levels. More specifically, a triplet loss is used at the column level to learn embeddings, while fine-tuning LLMs is employed at the database level for schema reasoning. MSL employs classifier and similarity scores to model schema interactions for schema linking at the table level. In particular, PSM-SQL adopts a chain loop strategy to reduce the task difficulty of schema linking by continuously reducing the number of redundant schemas. Experiments conducted on text-to-SQL datasets show that the proposed PSM-SQL is 1-3 percentage points higher than the existing methods.

Problem

• Convert natural language to SQL queries
• Reduce redundant database schemas
• Improve multi-granularity schema learning

Innovation

• Multi-granularity schema linking
• Triplet loss embeddings
• Chain loop strategy