面向 Text-to-SQL 语义解析的错误检测
Error Detection for Text-to-SQL Semantic Parsing
AI总结：
本文提出独立于解析器的 text-to-SQL 错误检测模型，结合代码语言模型与图神经网络学习问题和 SQL 结构，并在跨领域真实错误上训练，实验证明其优于解析器相关不确定性指标。
摘要：
尽管近年来 text-to-SQL 语义解析取得了显著进展，但现有解析器的性能仍远非完美。具体而言，基于深度学习的现代 text-to-SQL 解析器往往过度自信，因此在实际部署时其可信度令人怀疑。本文提出一种独立于解析器的 text-to-SQL 语义解析错误检测模型。该模型以代码语言模型为基础，并利用图神经网络加以增强，以学习自然语言问题和 SQL 查询的结构特征。我们在跨领域设置中收集的真实解析错误上训练模型，从而获得更强的泛化能力。针对三个具有不同解码机制的强 text-to-SQL 解析器的实验表明，我们的方法优于依赖解析器的不确定性指标。无论解析器采用何种架构，该模型都能有效提升 text-to-SQL 语义解析器的性能和可用性。（实现见 https://github.com/OSU-NLP-Group/Text2SQL-Error-Detection）
英文摘要：
Despite remarkable progress in text-to-SQL semantic parsing in recent years, the performance of existing parsers is still far from perfect. Specifically, modern text-to-SQL parsers based on deep learning are often over-confident, thus casting doubt on their trustworthiness when deployed for real use. In this paper, we propose a parser-independent error detection model for text-to-SQL semantic parsing. Using a language model of code as its bedrock, we enhance our error detection model with graph neural networks that learn structural features of both natural language questions and SQL queries. We train our model on realistic parsing errors collected from a cross-domain setting, which leads to stronger generalization ability. Experiments with three strong text-to-SQL parsers featuring different decoding mechanisms show that our approach outperforms parser-dependent uncertainty metrics. Our model could also effectively improve the performance and usability of text-to-SQL semantic parsers regardless of their architectures. (Our implementation is available at https://github.com/OSU-NLP-Group/Text2SQL-Error-Detection)
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。
