优化自然语言转SQL的流水线，发现组件间存在复杂交互关系。
The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactions
- 引入中间表示、预处理、合成数据微调和新重排序器。
- 组合所有组件未达最佳，性能依赖组件间相互作用。
- 适合想构建轻量高效NL2SQL系统的研究者参考。
大语言模型时代下，自然语言转SQL仍是开放问题，应用广泛。本文系统分析了NL2SQL流水线中多个扩展模块的交互机制，以启发更轻量级模型的设计。具体包括：采用NatSQL中间表示、增加预处理与基于合成数据的微调步骤，并提出一种新型重排序模型提升最终束搜索中的SQL选择质量。在SmBoP与RASAT两种主干架构上进行了消融实验，并结合Shapley值分析各组件影响。结果表明，简单堆叠所有组件并不能获得最优效果，各模块的表现取决于其与基线系统及其他组件的相互作用。
原文摘要 · Abstract (English)
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.
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。