用新中间表示EzSQL让数据库查询更像自然语言，提升生成效果。
EzSQL: An SQL intermediate representation for improving SQL-to-text Generation
- 设计EzSQL中间表示，简化SQL语法使其贴近自然语言
- 在WikiSQL和Spider数据集上达到当前最佳生成效果
- 适合需要高质量SQL描述生成的研究者与开发者
传统SQL到文本生成任务采用模板、序列到序列、树到序列及图到序列模型。近期方法在序列到序列框架中利用预训练生成模型，但将SQL直接视为输入序列并非最优。本文提出一种新的SQL中间表示EzSQL，通过修改操作符和关键词，使SQL更接近自然语言表达，且无需集合运算符。该模型以EzSQL为输入，结合预训练生成模型，实现高质量文本生成。实验表明，在WikiSQL和Spider数据集上，该方法为当前最优。此外，使用该模型生成的预训练数据可进一步提升Text-to-SQL解析器性能。
原文摘要 · Abstract (English)
The SQL-to-text generation task traditionally uses template base, Seq2Seq, tree-to-sequence, and graph-to-sequence models. Recent models take advantage of pre-trained generative language models for this task in the Seq2Seq framework. However, treating SQL as a sequence of inputs to the pre-trained models is not optimal. In this work, we put forward a new SQL intermediate representation called EzSQL to align SQL with the natural language text sequence. EzSQL simplifies the SQL queries and brings them closer to natural language text by modifying operators and keywords, which can usually be described in natural language. EzSQL also removes the need for set operators. Our proposed SQL-to-text generation model uses EzSQL as the input to a pre-trained generative language model for generating the text descriptions. We demonstrate that our model is an effective state-of-the-art method to generate text narrations from SQL queries on the WikiSQL and Spider datasets. We also show that by generating pretraining data using our SQL-to-text generation model, we can enhance the performance of Text-to-SQL parsers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。