文献类型：期刊文献

中文题名：基于预训练机制的自修正复杂语义分析方法

英文题名：Self-correcting complex semantic analysis method based on pre-training mechanism

作者：李青[1];钟将[1];李立力[2];李琪[3]

机构：[1]重庆大学计算机学院,重庆400044;[2]重庆大学土木工程学院,重庆400044;[3]绍兴文理学院计算机科学与工程系,浙江绍兴312000

年份：2019

卷号：40

期号：12

起止页码：41

中文期刊名：通信学报

外文期刊名：Journal on Communications

收录：CSTPCD、、EI(收录号：20200508107946)、北大核心2017、Scopus(收录号：2-s2.0-85078537646)、CSCD2019_2020、北大核心、CSCD

基金：Fundamental Research Funds for the Central Universities (No.2018CDYJSY0055), The National Key Research and Development Program of China (No.2017YFB1402400), Graduate Research and Innovation Foundation of Chongqing (No.CYB18058), Chongqing Technological Innovation and Application Demonstration Project (No.cstc2018jszx-cyzdX0086).

语种：中文

中文关键词：文本到SQL;语义分析;自然语言处理;复杂事件处理

外文关键词：Text-to-SQL;semantic parsing;natural language processing;complex event processing

中文摘要：面向知识服务过程中内容资源的智能化、知识化、精细化和重组化的碎片性管理需求。深层分析并挖掘语义隐层知识、技术、经验与信息,突破已有传统文本到结构化查询语言(SQL)的语义分析技术瓶颈,提出基于预训练机制的自修正复杂语义分析方法PT-Sem2SQL。设计结合Kullback-Leibler差异技术的MT-DNN预训练机制,以加强上下文语义理解深度;设计专有增强模块,捕获句内上下文语义信息的位置;并通过自修正方法优化生成模型的执行过程,以解决解码过程中的错误输出。实验结果表明,PT-Sem2SQL能够有效提高复杂语义的解析性能,准确度优于相关工作。

外文摘要：In the process of knowledge service,in order to meet the fragmentation management needs of intellectualization,knowledge ability,refinement and reorganization content resources.Through deep analysis and mining of semantic hidden knowledge,technology,experience,and information,it broke through the existing bottleneck of traditional semantic parsing technology from Text-to-SQL.The PT-Sem2SQL based on the pre-training mechanism was proposed.The MT-DNN pre-training model mechanism combining Kullback-Leibler technology was designed to enhance the depth of context semantic understanding.A proprietary enhancement module was designed that captured the location of contextual semantic information within the sentence.Optimize the execution process of the generated model by the self-correcting method to solve the error output during decoding.The experimental results show that PT-Sem2SQL can effectively improve the parsing performance of complex semantics,and its accuracy is better than related work.