发表机构
Huawei Ireland Research Centre（华为爱尔兰研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究NL2SQL翻译问题，通过集成NatSQL中间表示、增加预处理和微调步骤、开发重排器模型等方法，并结合SmBoP和RASAT架构进行消融及Shapley分析，揭示组件交互对结果的影响，为轻量级模型开发提供参考。
AI 中文摘要
在大语言模型时代，自然语言到SQL（NL2SQL）翻译仍是一个存在诸多实用应用的开放问题。我们探索了几种NL2SQL管道扩展之间的交互，以促进更轻量级模型的开发。具体而言，我们集成了NatSQL中间表示，纳入基于合成数据的预处理步骤和微调步骤，并开发了一种新颖的重排器模型以改进最终束搜索中的SQL选择。我们结合SmBoP和RASAT这两种骨干架构，对这些不同组件进行了消融研究并辅以Shapley分析。我们发现简单组合所有组件并不会带来最佳结果，其影响取决于它们与基线系统以及彼此之间的交互。
英文摘要
In the age of large language models, Natural Language to SQL (NL2SQL) translation remains an open problem with many useful applications. We explore interactions between several NL2SQL pipeline extensions to inspire development of more lightweight models. Specifically, we integrate the NatSQL intermediate representation, include a preprocessing step and a fine-tuning step based on synthetic data, and develop a novel reranker model to improve SQL selection in the final beam. We perform an ablation study supplemented by a Shapley analysis of these different components integrated with two backbone architectures, SmBoP and RASAT. We find that simply combining all of them does not lead to best results, but that their impact depends on their interactions with the baseline system, as well as each other.
