arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.10254cs.LGcs.DB
收藏

T5QL:用于生成SQL的驯服语言模型

T5QL: Taming language models for SQL generation

Outsystems(奥系统)

Samuel Arcadinho, David Aparício, Hugo Veiga, António Alegria

摘要:

自动SQL生成一直是一个活跃的研究领域,旨在通过编写具有给定意图的自然语言而不是编写SQL来简化对数据库的访问。当前用于语义解析的SOTA方法依赖于LLM来实现对基准数据集的高预测精度。这降低了它们的适用性,因为LLM需要昂贵的GPU。此外,SOTA方法是不接地的,因此不能保证总是生成有效的SQL。在这里,我们提出了T5 QL,一个新的SQL生成方法,提高了性能的基准数据集时,使用较小的LM,即T5-基地,由13 PP相比,SOTA方法。此外,T5 QL使用上下文无关文法来约束SQL生成,从而保证始终输出有效的SQL。最后,我们表明,划分语义解析在两个任务,候选SQL生成和候选重新排名,是一个很有前途的研究途径,可以减少对大型LM的需要。

英文摘要:

Automatic SQL generation has been an active research area, aiming at streamlining the access to databases by writing natural language with the given intent instead of writing SQL. Current SOTA methods for semantic parsing depend on LLMs to achieve high predictive accuracy on benchmark datasets. This reduces their applicability, since LLMs requires expensive GPUs. Furthermore, SOTA methods are ungrounded and thus not guaranteed to always generate valid SQL. Here we propose T5QL, a new SQL generation method that improves the performance in benchmark datasets when using smaller LMs, namely T5-Base, by 13pp when compared against SOTA methods. Additionally, T5QL is guaranteed to always output valid SQL using a context-free grammar to constrain SQL generation. Finally, we show that dividing semantic parsing in two tasks, candidate SQLs generation and candidate re-ranking, is a promising research avenue that can reduce the need for large LMs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑