跨数据库映射SQL查询，提升文本转SQL的准确率
SQL-Exchange: Transforming SQL Queries Across Domains
- 保留源查询结构，适配目标数据库字段与表名
- 映射后查询在多个数据集上执行有效且语义正确
- 适合需要跨领域迁移的文本转SQL系统开发者
我们提出SQL-Exchange框架，通过保持源查询结构的同时，将领域特定元素适配至目标数据库模式，实现跨数据库的SQL查询映射。研究了此类映射的可行性与收益，并评估其对文本转SQL系统上下文学习性能的影响。在多模型族与基准数据集上的综合评估显示，该方法在多种模式和查询类型下均有效。结果表明，使用映射后的查询进行上下文提示或在映射数据上微调，均显著优于直接使用源模式数据的性能。
原文摘要 · Abstract (English)
We introduce SQL-Exchange, a framework for mapping SQL queries across different database schemas by preserving the source query structure while adapting domain-specific elements to align with the target schema. We investigate the conditions under which such mappings are feasible and beneficial, and examine their impact on enhancing the in-context learning performance of text-to-SQL systems as a downstream task. Our comprehensive evaluation across multiple model families and benchmark datasets -- assessing structural alignment with source queries, execution validity on target databases, and semantic correctness -- demonstrates that SQL-Exchange is effective across a wide range of schemas and query types. Our results further show that both in-context prompting with mapped queries and fine-tuning on mapped data consistently yield higher text-to-SQL performance than using examples drawn directly from the source schema.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。