Proj AutoWriter Paper Reading: Knowledge-based type-aware neural text-to-sql generation
作者:互联网
TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation
Abstract
- 介绍relational db
- 介绍Task
本文: TypeSQL
方法: 将问题转化为slot filling task
同时利用了type information
实验:
数据集: WikiSQL
效果: +5.5%的同时减少时间 - 显示了读取数据库能极大地增强对不规范查询的效果
- 相较于目前的content-sensitive model,+82.6%精度, +17.5%绝对提升
标签:based,Knowledge,neural,generation,text,TypeSQL,Based,type 来源: https://www.cnblogs.com/xuesu/p/15627256.html