Application of LSA space's dimension character in document multi-hierarchy clustering

Yun Feng Liu, Huan Qi, Xiang En Hu, Zhi Qiang Cai, Jianmin Dai, Li Zhu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In LSA space, dimensions corresponding to bigger singular values reflect the general concept of language elements, while dimensions corresponding to smaller singular values reflect particular concept of language elements. On this basis, different dimensions of LSA space are adopted for document clustering under various concept granularities. In addition, in the LSA-based algorithm of document clustering, better clustering results are obtained by taking the row vectors of document self-indexing matrix as the objects to be clustered, instead of the document vectors with low dimensionality.

Original languageEnglish (US)
Title of host publication2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005
Pages2384-2389
Number of pages6
StatePublished - Dec 12 2005
Externally publishedYes
EventInternational Conference on Machine Learning and Cybernetics, ICMLC 2005 - Guangzhou, China
Duration: Aug 18 2005Aug 21 2005

Other

OtherInternational Conference on Machine Learning and Cybernetics, ICMLC 2005
CountryChina
CityGuangzhou
Period8/18/058/21/05

Keywords

  • Concept Granularity
  • Document Multi-hierarchy Clustering
  • Document Self-indexing Matrix
  • Latent Semantic Analysis

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Liu, Y. F., Qi, H., Hu, X. E., Cai, Z. Q., Dai, J., & Zhu, L. (2005). Application of LSA space's dimension character in document multi-hierarchy clustering. In 2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005 (pp. 2384-2389)

Application of LSA space's dimension character in document multi-hierarchy clustering. / Liu, Yun Feng; Qi, Huan; Hu, Xiang En; Cai, Zhi Qiang; Dai, Jianmin; Zhu, Li.

2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005. 2005. p. 2384-2389.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, YF, Qi, H, Hu, XE, Cai, ZQ, Dai, J & Zhu, L 2005, Application of LSA space's dimension character in document multi-hierarchy clustering. in 2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005. pp. 2384-2389, International Conference on Machine Learning and Cybernetics, ICMLC 2005, Guangzhou, China, 8/18/05.
Liu YF, Qi H, Hu XE, Cai ZQ, Dai J, Zhu L. Application of LSA space's dimension character in document multi-hierarchy clustering. In 2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005. 2005. p. 2384-2389
Liu, Yun Feng ; Qi, Huan ; Hu, Xiang En ; Cai, Zhi Qiang ; Dai, Jianmin ; Zhu, Li. / Application of LSA space's dimension character in document multi-hierarchy clustering. 2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005. 2005. pp. 2384-2389
@inproceedings{743b7cb0fd6f49ec9726911deb8e1eb2,
title = "Application of LSA space's dimension character in document multi-hierarchy clustering",
abstract = "In LSA space, dimensions corresponding to bigger singular values reflect the general concept of language elements, while dimensions corresponding to smaller singular values reflect particular concept of language elements. On this basis, different dimensions of LSA space are adopted for document clustering under various concept granularities. In addition, in the LSA-based algorithm of document clustering, better clustering results are obtained by taking the row vectors of document self-indexing matrix as the objects to be clustered, instead of the document vectors with low dimensionality.",
keywords = "Concept Granularity, Document Multi-hierarchy Clustering, Document Self-indexing Matrix, Latent Semantic Analysis",
author = "Liu, {Yun Feng} and Huan Qi and Hu, {Xiang En} and Cai, {Zhi Qiang} and Jianmin Dai and Li Zhu",
year = "2005",
month = "12",
day = "12",
language = "English (US)",
isbn = "078039092X",
pages = "2384--2389",
booktitle = "2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005",

}

TY - GEN

T1 - Application of LSA space's dimension character in document multi-hierarchy clustering

AU - Liu, Yun Feng

AU - Qi, Huan

AU - Hu, Xiang En

AU - Cai, Zhi Qiang

AU - Dai, Jianmin

AU - Zhu, Li

PY - 2005/12/12

Y1 - 2005/12/12

N2 - In LSA space, dimensions corresponding to bigger singular values reflect the general concept of language elements, while dimensions corresponding to smaller singular values reflect particular concept of language elements. On this basis, different dimensions of LSA space are adopted for document clustering under various concept granularities. In addition, in the LSA-based algorithm of document clustering, better clustering results are obtained by taking the row vectors of document self-indexing matrix as the objects to be clustered, instead of the document vectors with low dimensionality.

AB - In LSA space, dimensions corresponding to bigger singular values reflect the general concept of language elements, while dimensions corresponding to smaller singular values reflect particular concept of language elements. On this basis, different dimensions of LSA space are adopted for document clustering under various concept granularities. In addition, in the LSA-based algorithm of document clustering, better clustering results are obtained by taking the row vectors of document self-indexing matrix as the objects to be clustered, instead of the document vectors with low dimensionality.

KW - Concept Granularity

KW - Document Multi-hierarchy Clustering

KW - Document Self-indexing Matrix

KW - Latent Semantic Analysis

UR - http://www.scopus.com/inward/record.url?scp=28444478040&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28444478040&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:28444478040

SN - 078039092X

SN - 9780780390928

SP - 2384

EP - 2389

BT - 2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005

ER -