arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.16613cs.CLcs.AIcs.LG
收藏

用于Text-to-SQL解析器跨数据库适配的多样并行数据合成

Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers

Indian Institute of Technology Bombay(印度理工学院孟买分校)

Abhijeet Awasthi, Ashutosh Sathe, Sunita Sarawagi

摘要:

文本到SQL解析器通常在训练期间与看不见的数据库作斗争。由于新模式中缺少自然语言查询,使解析器适应新数据库是一个具有挑战性的问题。我们提出了ReFill,一个框架,用于合成高质量和文本多样的并行数据集,以适应文本到SQL解析器的目标模式。ReFill学习从现有模式中检索和编辑文本查询,并将其传输到目标模式。我们发现,检索不同的现有文本,掩盖其特定于模式的令牌,并重新填充与目标模式相关的令牌,导致更多样化的文本查询比标准的SQL到文本生成方法。通过跨多个数据库的实验,我们证明了使用ReFill合成的数据集上的微调解析器始终优于先前的数据增强方法。

英文摘要:

Text-to-SQL parsers typically struggle with databases unseen during the train time. Adapting parsers to new databases is a challenging problem due to the lack of natural language queries in the new schemas. We present ReFill, a framework for synthesizing high-quality and textually diverse parallel datasets for adapting a Text-to-SQL parser to a target schema. ReFill learns to retrieve-and-edit text queries from the existing schemas and transfers them to the target schema. We show that retrieving diverse existing text, masking their schema-specific tokens, and refilling with tokens relevant to the target schema, leads to significantly more diverse text queries than achievable by standard SQL-to-Text generation methods. Through experiments spanning multiple databases, we demonstrate that fine-tuning parsers on datasets synthesized using ReFill consistently outperforms the prior data-augmentation methods.

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。

↑