论文标题
部分可观测时空混沌系统的无模型预测
Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL
论文作者
论文摘要
文本到SQL的任务旨在将自然语言问题转换为其在关系表的背景下的相应SQL查询。现有的文本到SQL解析器为任意用户问题生成一个“合理” SQL查询，从而无法正确处理有问题的用户问题。为了正式解决这个问题，我们对文本到SQL中观察到的模棱两可和无法回答的病例进行了初步研究，并将其分为6个特征类别。相应地，我们确定了每个类别背后的原因，并提出了处理模棱两可和无法回答的问题的要求。在这项研究之后，我们提出了一种简单而有效的反事实示例生成方法，该方法会自动产生模棱两可且无法回答的文本到SQL示例。此外，我们提出了一个弱监督的DTE（检测到解释）模型，以进行错误检测，定位和解释。实验结果表明，与各种基线相比，我们的模型在现实世界中都可以达到最佳结果。我们在以下位置发布数据和代码：\ href {https://github.com/wbbeyourself/dte} {https://github.com/wbbeyourself/dte}。
The task of text-to-SQL aims to convert a natural language question into its corresponding SQL query within the context of relational tables. Existing text-to-SQL parsers generate a "plausible" SQL query for an arbitrary user question, thereby failing to correctly handle problematic user questions. To formalize this problem, we conduct a preliminary study on the observed ambiguous and unanswerable cases in text-to-SQL and summarize them into 6 feature categories. Correspondingly, we identify the causes behind each category and propose requirements for handling ambiguous and unanswerable questions. Following this study, we propose a simple yet effective counterfactual example generation approach that automatically produces ambiguous and unanswerable text-to-SQL examples. Furthermore, we propose a weakly supervised DTE (Detecting-Then-Explaining) model for error detection, localization, and explanation. Experimental results show that our model achieves the best result on both real-world examples and generated examples compared with various baselines. We release our data and code at: \href{https://github.com/wbbeyourself/DTE}{https://github.com/wbbeyourself/DTE}.
