论文标题
tableqa：用于表吸引SQL生成的大型中文文本到SQL数据集
TableQA: a Large-Scale Chinese Text-to-SQL Dataset for Table-Aware SQL Generation
论文作者
论文摘要
用数据驱动的方法（如深神经网络）将自然语言解析到相应的SQL（NL2SQL）近年来引起了很多关注。现有的NL2SQL数据集假定条件值应完全出现在自然语言问题中，并且鉴于表可以回答查询。但是，在实际情况下，这些假设可能会失败，因为用户可以对表中的相同内容使用不同的表达式，并且在表格外部查询信息，而没有表格中的内容。因此，我们向SQL数据集提供TableQA，这是一种大规模的跨域自然语言，中文数据集，其中64,891个问题和20,311个独特的SQL查询超过6,000张桌子。与对NL2SQL数据集的重新分配不同，TableQA不仅需要概括为不同问题和表格架的SQL骨骼，还需要对条件值的各种表达式进行概括。实验结果表明，WikISQL上具有95.1％条件价值准确性的最新模型仅获得46.8％的条件值准确度和43.0％的逻辑形式的精度，这表明所提出的数据集具有挑战性且需要处理。提出了两种表达方法来减轻问题，端到端方法在条件值和逻辑表单上获得了51.3％和47.4％的精度，分别提高了4.7％和3.4％。
Parsing natural language to corresponding SQL (NL2SQL) with data driven approaches like deep neural networks attracts much attention in recent years. Existing NL2SQL datasets assume that condition values should appear exactly in natural language questions and the queries are answerable given the table. However, these assumptions may fail in practical scenarios, because user may use different expressions for the same content in the table, and query information outside the table without the full picture of contents in table. Therefore we present TableQA, a large-scale cross-domain Natural Language to SQL dataset in Chinese language consisting 64,891 questions and 20,311 unique SQL queries on over 6,000 tables. Different from exisiting NL2SQL datasets, TableQA requires to generalize well not only to SQL skeletons of different questions and table schemas, but also to the various expressions for condition values. Experiment results show that the state-of-the-art model with 95.1% condition value accuracy on WikiSQL only gets 46.8% condition value accuracy and 43.0% logic form accuracy on TableQA, indicating the proposed dataset is challenging and necessary to handle. Two table-aware approaches are proposed to alleviate the problem, the end-to-end approaches obtains 51.3% and 47.4% accuracy on the condition value and logic form tasks, with improvement of 4.7% and 3.4% respectively.
