| 注册
首页|期刊导航|高技术通讯|融合关联语义信息的工程领域标准规范表格检索方法

融合关联语义信息的工程领域标准规范表格检索方法

徐雪松 肖刚 刘星光 张侠 叶江涛 程振波

高技术通讯2025,Vol.35Issue(7):724-733,10.
高技术通讯2025,Vol.35Issue(7):724-733,10.DOI:10.3772/j.issn.1002-0470.2025.07.005

融合关联语义信息的工程领域标准规范表格检索方法

Table retrieval method for engineering standard specifications with correlated semantic information

徐雪松 1肖刚 2刘星光 3张侠 4叶江涛 2程振波2

作者信息

  • 1. 浙江工业大学机械工程学院 杭州 310023||浙江工业大学计算机科学与技术学院 杭州 310023
  • 2. 浙江工业大学计算机科学与技术学院 杭州 310023
  • 3. 行吟信息科技(上海)有限公司 上海 200003
  • 4. 浙江工业大学机械工程学院 杭州 310023
  • 折叠

摘要

Abstract

According to the characteristics of tables in engineering standard specifications,a method is proposed to achieve automatic retrieval of their associated tables via query sentences by constructing a concentration joint repre-sentation between query sentences and multiple attributes of tables.Firstly,the concentration vector is obtained by calculating the pre-concentration between the keywords of the query and the attributes of the table title,table header and cells.Subsequently,the joint vector of query and tables is obtained by the bidirectional long short term memory network(Bi-LSTM)and multi-headed self-attention(MHA).Then,the concentration-joint representation between query and tables is constructed by fusing the concentration vector with the joint vector.Finally,the concentration-joint vector is input to the single-layer perceptron to obtain the similarity between query and tables.Experimental verification is carried out on the publicly available Chinese table datasets and constructed table datasets of engineer-ing fields,which shows that the proposed method has significant superiority in retrieval accuracy.

关键词

表格检索/特征融合/自然语言处理/语义表示/标准规范

Key words

table retrieval/feature fusion/natural language processing/semantic representation/standard spec-ification

引用本文复制引用

徐雪松,肖刚,刘星光,张侠,叶江涛,程振波..融合关联语义信息的工程领域标准规范表格检索方法[J].高技术通讯,2025,35(7):724-733,10.

基金项目

国家自然科学基金面上项目(61976193)和浙江省"尖兵""领雁"研发攻关计划(2023C01215,2023C01022)资助项目. (61976193)

高技术通讯

OA北大核心

1002-0470

访问量0
|
下载量0
段落导航相关论文