We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycle-consistent examples to adapt the parser. Unlike data-augmentation, which typically synthesizes unverified examples in the training environment, GAZP synthesizes examples in the new environment whose input-output consistency are verified. On the Spider, Sparc, and CoSQL zero-shot semantic parsing tasks, GAZP improves logical form and execution accuracy of the baseline parser. Our analyses show that GAZP outperforms data-augmentation in the training environment, performance increases with the amount of GAZP-synthesized data, and cycle-consistency is central to successful adaptation.

中文翻译：

---

零样本可执行语义解析的接地适配

我们提出了零样本可执行语义解析（GAZP）的基础适应，以使现有的语义解析器适应新环境（例如新数据库模式）。GAZP 将前向语义解析器与后向话语生成器结合起来，在新环境中合成数据（例如话语和 SQL 查询），然后选择循环一致的示例来适应解析器。与通常在训练环境中合成未经验证的示例的数据增强不同，GAZP 在新环境中合成输入-输出一致性得到验证的示例。在 Spider、Sparc 和 CoSQL 零样本语义解析任务上，GAZP 提高了基线解析器的逻辑形式和执行精度。我们的分析表明，GAZP 在训练环境中的表现优于数据增强，