NSL OpenIR  > 中国科学院兰州文献情报中心  > 资源系统建设部
基于深度学习的领域本体概念自动获取方法研究
Alternative TitleMethod of Domain Ontology Concept Automatic Extraction Based on Deep Learning
王思丽1,2,3; 祝忠明1,2; 刘巍1,2; 杨恒1,2
2019-10-28
Source Publication情报理论与实践
ISSN1000-7490
Issue10Pages:1-13
Contribution Rank1
Abstract

[目的/意义]实现对领域概念的自动学习抽取,解决领域本体自动化构建的首要基础任务。[方法/过程]以无监督的学习方法和端到端的识别模式为理论技术基础,首先通过对主流词嵌入模型进行对比分析,设计提出了基于Word2Vec和Skip-Gram的领域文本特征词嵌入模型的自动生成方法;其次研究构建了以IOB格式的标注文本作为输入,基于自注意力机制的BLSTM-CRF领域概念自动抽取模型;最后以资源环境学科领域为例进行了实验研究与评估分析。[结果/结论]模型能够实现对领域概念的自动抽取,对领域新概念或术语的自动识别也具有一定的健壮性。[局限]模型精度尚未达到峰值,有待进一步优化提升。 

Other Abstract

[Purpose/significance] Realize the automatic learning extraction of domain concepts and solve the primary basic tasks of domain ontology automation construction.[Method/process] The unsupervised learning method and the end-to-end recognition mode are the theoretical and technical foundations. Firstly, through the comparative analysis of the mainstream word embedding model, the paper designs an automatic generation method of domain text feature word embedding model based on Word2Vec and Skip-Gram. Secondly, the paper constructs a domain concept automatic extraction model named BLSTM-CRF based on self-attention mechanism, using annotated text in IOB format as input. Finally, the paper takes the field of resources and environment as an example to carry out experimental research and evaluation analysis. [Result/conclusion] The model can realize the automatic extraction of the domain concepts, and it also has certain robustness to the automatic identification of new domain concepts or terms. [Limitations] The accuracy of the model has not yet reached the top value and needs to be further optimized.

Keyword深度学习 领域本体 概念自动获取 词嵌入 自注意力
MOST Discipline Catalogue管理学 ; 管理学::图书情报与档案管理
URL查看原文
Indexed ByCSSCI ; 中文核心期刊要目总览
Language中文
Funding Project基于深度学习的领域本体自动构建方法研究
Document Type期刊论文
Identifierhttp://ir.las.ac.cn/handle/12502/10532
Collection中国科学院兰州文献情报中心_资源系统建设部
Affiliation1.中国科学院西北生态环境资源研究院文献情报中心
2.中国科学院兰州文献情报中心
3.中国科学院大学
First Author Affilication中国科学院文献情报中心
Recommended Citation
GB/T 7714
王思丽,祝忠明,刘巍,等. 基于深度学习的领域本体概念自动获取方法研究[J]. 情报理论与实践,2019(10):1-13.
APA 王思丽,祝忠明,刘巍,&杨恒.(2019).基于深度学习的领域本体概念自动获取方法研究.情报理论与实践(10),1-13.
MLA 王思丽,et al."基于深度学习的领域本体概念自动获取方法研究".情报理论与实践 .10(2019):1-13.
Files in This Item: Download All
File Name/Size DocType Version Access License
基于深度学习的领域本体概念自动获取方法研(563KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[王思丽]'s Articles
[祝忠明]'s Articles
[刘巍]'s Articles
Baidu academic
Similar articles in Baidu academic
[王思丽]'s Articles
[祝忠明]'s Articles
[刘巍]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[王思丽]'s Articles
[祝忠明]'s Articles
[刘巍]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于深度学习的领域本体概念自动获取方法研究_王思丽.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.