• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于语义多样性的段落嵌入资金地图。

Funding map using paragraph embedding based on semantic diversity.

作者信息

Kawamura Takahiro, Watanabe Katsutaro, Matsumoto Naoya, Egami Shusaku, Jibu Mari

机构信息

Japan Science and Technology Agency, Tokyo, Japan.

出版信息

Scientometrics. 2018;116(2):941-958. doi: 10.1007/s11192-018-2783-x. Epub 2018 May 28.

DOI:10.1007/s11192-018-2783-x
PMID:30147200
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC6096681/
Abstract

Maps of science representing the structure of science can help us understand science and technology (S&T) development. Studies have thus developed techniques for analyzing research activities' relationships; however, ongoing research projects and recently published papers have difficulty in applying inter-citation and co-citation analysis. Therefore, in order to characterize what is currently being attempted in the scientific landscape, this paper proposes a new content-based method of locating research projects in a multi-dimensional space using the recent word/paragraph embedding techniques. Specifically, for addressing an problem associated with the original paragraph vectors, we introduce paragraph vectors based on the information entropies of concepts in an S&T thesaurus. The experimental results show that the proposed method successfully formed a clustered map from 25,607 project descriptions of the 7th Framework Programme of EU from 2006 to 2016 and 34,192 project descriptions of the National Science Foundation from 2012 to 2016.

摘要

呈现科学结构的科学图谱有助于我们理解科学技术（S&T）的发展。因此，已有研究开发出了分析研究活动之间关系的技术；然而，正在进行的研究项目和最近发表的论文难以应用相互引用和共被引分析。所以，为了刻画当前科学领域正在尝试的内容，本文提出了一种基于内容的新方法，利用最近的词/段落嵌入技术在多维空间中定位研究项目。具体而言，为了解决与原始段落向量相关的问题，我们引入了基于科技词库中概念信息熵的段落向量。实验结果表明，该方法成功地从2006年至2016年欧盟第七框架计划的25607个项目描述以及2012年至2016年美国国家科学基金会的34192个项目描述中形成了聚类图谱。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/b63fe1317be0/11192_2018_2783_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/69b37a5ee865/11192_2018_2783_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/7f4c799fdd1c/11192_2018_2783_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/54760737311e/11192_2018_2783_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/ce8912e75555/11192_2018_2783_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/82d5949dec95/11192_2018_2783_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/acba1a9bbe03/11192_2018_2783_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/6ab12b71a651/11192_2018_2783_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/3e6dd2887245/11192_2018_2783_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/eb75e316b5c6/11192_2018_2783_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/b63fe1317be0/11192_2018_2783_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/69b37a5ee865/11192_2018_2783_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/7f4c799fdd1c/11192_2018_2783_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/54760737311e/11192_2018_2783_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/ce8912e75555/11192_2018_2783_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/82d5949dec95/11192_2018_2783_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/acba1a9bbe03/11192_2018_2783_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/6ab12b71a651/11192_2018_2783_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/3e6dd2887245/11192_2018_2783_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/eb75e316b5c6/11192_2018_2783_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ca33/6096681/b63fe1317be0/11192_2018_2783_Fig10_HTML.jpg

相似文献

1
Funding map using paragraph embedding based on semantic diversity.基于语义多样性的段落嵌入资金地图。
Scientometrics. 2018;116(2):941-958. doi: 10.1007/s11192-018-2783-x. Epub 2018 May 28.
2
Experience of King Abdul-Aziz City for science and technology in funding medical research in Saudi Arabia.阿卜杜勒-阿齐兹国王科技城在沙特阿拉伯资助医学研究的经验。
Saudi Med J. 2004 Jan;25(1 Suppl):S8-12.
3
[Continuous funding of National Natural Science Foundation of China has boosted the development of the discipline of ophthalmology over the past 25 years].在过去25年里，国家自然科学基金的持续资助推动了眼科学科的发展。
Zhonghua Yan Ke Za Zhi. 2012 Feb;48(2):164-9.
4
Diabetic nephropathy research in China: Data analysis and review from the National Natural Science Foundation of China.中国糖尿病肾病研究：基于国家自然科学基金的数据分析与综述
J Diabetes. 2015 May;7(3):307-14. doi: 10.1111/1753-0407.12265. Epub 2015 Apr 14.
5
Effective Multimodal Encoding for Image Paragraph Captioning.用于图像段落字幕的有效多模态编码
IEEE Trans Image Process. 2022;31:6381-6395. doi: 10.1109/TIP.2022.3211467. Epub 2022 Oct 18.
6
cite2vec: Citation-Driven Document Exploration via Word Embeddings.cite2vec：基于引文驱动的词向量文档探索。
IEEE Trans Vis Comput Graph. 2017 Jan;23(1):691-700. doi: 10.1109/TVCG.2016.2598667.
7
Facilitating Image Search With a Scalable and Compact Semantic Mapping.用可扩展和紧凑的语义映射来促进图像搜索。
IEEE Trans Cybern. 2015 Aug;45(8):1561-74. doi: 10.1109/TCYB.2014.2356136. Epub 2014 Sep 17.
8
Proceedings of the Second Workshop on Theory meets Industry (Erwin-Schrödinger-Institute (ESI), Vienna, Austria, 12-14 June 2007).第二届理论与产业研讨会会议录（2007年6月12日至14日，奥地利维也纳埃尔温·薛定谔研究所）
J Phys Condens Matter. 2008 Feb 13;20(6):060301. doi: 10.1088/0953-8984/20/06/060301. Epub 2008 Jan 24.
9
Views of the Medical Research Council on the Green Paper "A Framework for Government Research and Development".医学研究理事会对绿皮书《政府研发框架》的看法。
Br Med J. 1972 Feb 5;1(5796):357-60.
10
Enhancing MEDLINE document clustering by incorporating MeSH semantic similarity.通过整合 MeSH 语义相似度来增强 MEDLINE 文档聚类。
Bioinformatics. 2009 Aug 1;25(15):1944-51. doi: 10.1093/bioinformatics/btp338. Epub 2009 Jun 3.

引用本文的文献

1
Science maps for exploration, navigation, and reflection-A graphic approach to strategic thinking.科学图谱：探索、导航与反思——一种战略思维的图形方法。
PLoS One. 2021 Dec 31;16(12):e0262081. doi: 10.1371/journal.pone.0262081. eCollection 2021.

本文引用的文献

1
Database of NIH grants using machine-learned categories and graphical clustering.使用机器学习类别和图形聚类的美国国立卫生研究院资助数据库。
Nat Methods. 2011 Jun;8(6):443-4. doi: 10.1038/nmeth.1619.
2
Clustering more than two million biomedical publications: comparing the accuracies of nine text-based similarity approaches.对两百多万篇生物医学文献进行聚类：比较九种基于文本的相似度方法的准确性。
PLoS One. 2011 Mar 17;6(3):e18029. doi: 10.1371/journal.pone.0018029.
3
Finding scientific topics.寻找科学主题。
Proc Natl Acad Sci U S A. 2004 Apr 6;101 Suppl 1(Suppl 1):5228-35. doi: 10.1073/pnas.0307752101. Epub 2004 Feb 10.
4
NETWORKS OF SCIENTIFIC PAPERS.科学论文网络
Science. 1965 Jul 30;149(3683):510-5. doi: 10.1126/science.149.3683.510.