辅助任务增强的中文跨域NL2SQL算法OA北大核心CSTPCD
Chinese cross-domain NL2SQL algorithm enhanced by auxiliary task
自然语言到结构化查询语言(natural language to structured query language,NL2SQL)任务旨在将自然语言询问转化为数据库可执行的结构化查询语言(structured query language,SQL)语句.本文提出了一种辅助任务增强的中文跨域NL2SQL算法,其核心思想是通过在解码阶段添加辅助任务以结合原始模型来进行多任务训练,提升模型的准确率.辅助任务的设计是通过将数据库模式建模成图,预测自然语…查看全部>>
NL2SQL(natural language to structured query language)task aims to translate natural language queries into SQL(structured query language)executable by the database.A Chinese cross-domain NL2SQL algorithm enhanced by auxiliary tasks was proposed.Core idea was to perform multi-task training and improve the accuracy of the model by adding auxiliary tasks in the decoder and combining the prototype model.Auxiliary task was designed by modeling the database schema …查看全部>>
胡亚红;刘亚冬;朱正东;刘鹏杰
浙江工业大学计算机科学与技术学院,浙江杭州 310023西安交通大学软件学院,陕西西安 710049西安交通大学计算机科学与技术学院,陕西西安 710049西安交通大学计算机科学与技术学院,陕西西安 710049
计算机与自动化
人工智能深度学习自然语言处理语义解析
artificial intelligencedeep learningnatural language processingsemantic parsing
《国防科技大学学报》 2024 (2)
197-204,8
国家重点研发计划资助项目(2018YFB0204003,2018YFB0204004)
评论