文献类型：期刊文献

中文题名：图神经网络在Text-to-SQL解析中的技术研究

英文题名：Technical Research of Graph Neural Network for Text-to-SQL Parsing

作者：曹合心[1];赵亮[2];李雪峰[1]

机构：[1]同济大学电子与信息工程学院,上海201804;[2]华东理工大学信息科学与工程学院,上海200237

年份：2022

卷号：49

期号：4

起止页码：110

中文期刊名：计算机科学

外文期刊名：Computer Science

收录：CSTPCD;;北大核心:【北大核心2020】；CSCD:【CSCD_E2021_2022】；

基金：中央高校基本科研业务费专项资金(2212015665)。

语种：中文

中文关键词：Text-to-SQL解析;深度学习;图构建;图神经网络;多表SQL语句生成

外文关键词：Text-to-SQL parsing;Deep learning;Graph construction;Graph neural network;Multi-table SQL statement generation

摘要：语义解析领域中的Text-to-SQL任务对实现基于数据库的自动问答具有重要意义。现有深度学习模型,如Seq2Seq的序列生成模型在单表SQL查询中已取得显著效果,但无法解决多表SQL查询的问题。图神经网络能够有效提取数据库表和问句之间的关联信息,丰富解析过程中的语义信息,从而提升多表SQL查询的准确率。文中提出一种自适应的图构建方式和图编码方式,在现有Text-to-SQL模型中引入问句信息,通过对问句和数据库的拼接词向量进行卷积操作生成图网络初始化权重,对同种类型下的不同数据库可实现统一训练。采用IRNet框架和关系扩充的方式进行整体模型设计,在当前开放的Text-to-SQL数据集Spider上进行验证。结果表明,该技术能够有效提升多表SQL语句生成的匹配准确率,同时算法对图神经网络在Text-to-SQL领域的研究具有重要的参考价值。
The Text-to-SQL task in the field of semantic parsing is of great significance for realizing database-based automatic question and answer.At present,deep learning models,such as sequence generation model Seq2 Seq,has achieved significant effects in single-table SQL queries.However,the problem of multi-table SQL queries remains to be solved.Graph neural network can effectively extract the associated information between databases,tables and questions,enrich the semantic information in the parsing process,and improve the accuracy of multi-table SQL queries.This paper proposes an adaptive graph construction method and graph encoding method.Question information is introduced into the existing Text-to-SQL model,and the graph network initialized weights are generated by convolution operation on the splicing word vector of the question sentence and the database.General training can be achieved for different databases of the same type.The IRNet framework and relational expansion are used to design the overall model,and it is verified on the open Text-to-SQL data set——Spider.Results show that the technology can effectively improve the matching accuracy of multi-table SQL statement generation,and the algorithm has an important reference value for the research of graph neural network in the text-to-SQL field.