Abacus-SQL让自然语言直接查询跨领域数据库，自动找库并生成准确SQL。
Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrieval
- 通过数据库检索技术自动定位开放域中的目标数据库。
- 在多轮对话中实现90%以上的准确率，显著优于基线模型。
- 适合需要跨领域快速查询的开发者与数据分析师使用。
现有文本到SQL系统在生成SQL查询方面取得显著进展，但仍面临诸多挑战。现有系统普遍缺乏对开放域数据库的检索能力，用户需手动筛选相关数据库；同时其跨领域迁移能力有限，难以满足多样化的查询需求。为此，我们提出Abacus-SQL。该系统利用数据库检索技术，在开放域环境中精准定位所需数据库，并通过数据增强方法提升系统的跨领域迁移能力。此外，Abacus-SQL引入Pre-SQL与Self-debug机制，有效提升SQL生成准确性。实验结果表明，Abacus-SQL在多轮文本到SQL任务中表现优异，充分验证了该方法的有效性。Abacus-SQL已公开访问：https://huozi.8wss.com/abacus-sql/。
原文摘要 · Abstract (English)
The existing text-to-SQL systems have made significant progress in SQL query generation, but they still face numerous challenges. Existing systems often lack retrieval capabilities for open-domain databases, requiring users to manually filter relevant databases. Additionally, their cross-domain transferability is limited, making it challenging to accommodate diverse query requirements. To address these issues, we propose Abacus-SQL. Abacus-SQL utilizes database retrieval technology to accurately locate the required databases in an open-domain database environment. It also enhances the system cross-domain transfer ability through data augmentation methods. Moreover, Abacus-SQL employs Pre-SQL and Self-debug methods, thereby enhancing the accuracy of SQL queries. Experimental results demonstrate that Abacus-SQL performs excellently in multi-turn text-to-SQL tasks, effectively validating the approach's effectiveness. Abacus-SQL is publicly accessible at https://huozi.8wss.com/abacus-sql/.
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。