Turing：一个精确可解释的多假设跨领域自然语言数据库接口
Turing: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface
摘要：
自然语言数据库接口（NLDB）可以为非技术用户提供数据驱动的见解。然而，现有的文本到SQL语义解析器不能达到足够高的准确性，在跨数据库设置，以允许在实践中良好的可用性。这项工作提出了图灵，NLDB系统对弥合这一差距。图灵的跨域语义解析器与我们的新值预测方法实现了$75.1\%$执行精度，以及Spider验证集上的$78.3\%$ top-5 beam执行精度。为了从更高的波束精度中受益，我们设计了一个交互式系统，在该系统中，波束中的SQL假设用自然语言一步一步地解释，并突出显示它们的差异。然后，用户可以比较和判断的假设，以选择哪一个反映了他们的意图，如果有的话。图灵中SQL查询的英文解释是由我们基于同步语法的高精度自然语言生成系统生成的。
英文摘要：
A natural language database interface (NLDB) can democratize data-driven insights for non-technical users. However, existing Text-to-SQL semantic parsers cannot achieve high enough accuracy in the cross-database setting to allow good usability in practice. This work presents Turing, a NLDB system toward bridging this gap. The cross-domain semantic parser of Turing with our novel value prediction method achieves $75.1\%$ execution accuracy, and $78.3\%$ top-5 beam execution accuracy on the Spider validation set. To benefit from the higher beam accuracy, we design an interactive system where the SQL hypotheses in the beam are explained step-by-step in natural language, with their differences highlighted. The user can then compare and judge the hypotheses to select which one reflects their intention if any. The English explanations of SQL queries in Turing are produced by our high-precision natural language generation system based on synchronous grammars.
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。
