Learning the kernel matrix for XML document clustering

Jianwu Yang; Kwok Wai CHEUNG; Xiaoou Chen

doi:10.1109/EEE.2005.87

Learning the kernel matrix for XML document clustering

Jianwu Yang^*, Kwok Wai CHEUNG, Xiaoou Chen

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

18 Citations (Scopus)

Abstract

The rapid growth of XML adoption has urged for the need of a proper representation for semi-structured documents, where the document structural information has to be taken into account so as to support more precise document analysis. In this paper, an XML document representation named "structured link vector model" is adopted, with a kernel matrix included for modeling the similarity between XML elements. Our formulation allows individual XML elements to have their own weighted contribution to the overall document similarity while at the same time allows the between-clement similarity to be captured. An iterative algorithm is derived to learn the kernel matrix. For performance evaluation, the ACM SIGMOD Record dataset as well as the CEDE dataset have been tested. Our proposed method outperforms significantly the traditional vector space model and the edit-distance based methods. In addition, the kernel matrix obtained as a by-product provides knowledge about the conceptual relationship between the XML elements.

Original language	English
Title of host publication	Proceedings - 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05
Publisher	IEEE
Pages	353-358
Number of pages	6
ISBN (Print)	9780769522746, 0769522742
DOIs	https://doi.org/10.1109/EEE.2005.87
Publication status	Published - Apr 2005
Event	2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05 - Hong Kong, China Duration: 29 Mar 2005 → 1 Apr 2005 https://ieeexplore.ieee.org/xpl/conhome/9634/proceeding

Publication series

Name	Proceedings - IEEE International Conference on e-Technology, e-Commerce and e-Service

Conference

Conference	2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05
Country/Territory	China
City	Hong Kong
Period	29/03/05 → 1/04/05
Internet address	https://ieeexplore.ieee.org/xpl/conhome/9634/proceeding

User-Defined Keywords

Kernel
XML
Computer science
Text analysis
Information analysis
Iterative algorithms
Testing
Fourier transforms
Training data

Access to Document

10.1109/EEE.2005.87

Cite this

@inproceedings{cc9f5b77b8ac41908f746d2b5aeb8bab,

title = "Learning the kernel matrix for XML document clustering",

abstract = "The rapid growth of XML adoption has urged for the need of a proper representation for semi-structured documents, where the document structural information has to be taken into account so as to support more precise document analysis. In this paper, an XML document representation named {"}structured link vector model{"} is adopted, with a kernel matrix included for modeling the similarity between XML elements. Our formulation allows individual XML elements to have their own weighted contribution to the overall document similarity while at the same time allows the between-clement similarity to be captured. An iterative algorithm is derived to learn the kernel matrix. For performance evaluation, the ACM SIGMOD Record dataset as well as the CEDE dataset have been tested. Our proposed method outperforms significantly the traditional vector space model and the edit-distance based methods. In addition, the kernel matrix obtained as a by-product provides knowledge about the conceptual relationship between the XML elements.",

keywords = "Kernel, XML, Computer science, Text analysis, Information analysis, Iterative algorithms, Testing, Fourier transforms, Training data",

author = "Jianwu Yang and CHEUNG, {Kwok Wai} and Xiaoou Chen",

note = "Copyright: Copyright 2008 Elsevier B.V., All rights reserved.; 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05 ; Conference date: 29-03-2005 Through 01-04-2005",

year = "2005",

month = apr,

doi = "10.1109/EEE.2005.87",

language = "English",

isbn = "9780769522746",

series = "Proceedings - IEEE International Conference on e-Technology, e-Commerce and e-Service",

publisher = "IEEE",

pages = "353--358",

booktitle = "Proceedings - 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/9634/proceeding",

}

Yang, J, CHEUNG, KW & Chen, X 2005, Learning the kernel matrix for XML document clustering. in Proceedings - 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05. Proceedings - IEEE International Conference on e-Technology, e-Commerce and e-Service, IEEE, pp. 353-358, 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05, Hong Kong, China, 29/03/05. https://doi.org/10.1109/EEE.2005.87

Learning the kernel matrix for XML document clustering. / Yang, Jianwu; CHEUNG, Kwok Wai; Chen, Xiaoou.
Proceedings - 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05. IEEE, 2005. p. 353-358 (Proceedings - IEEE International Conference on e-Technology, e-Commerce and e-Service).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Learning the kernel matrix for XML document clustering

AU - Yang, Jianwu

AU - CHEUNG, Kwok Wai

AU - Chen, Xiaoou

PY - 2005/4

Y1 - 2005/4

N2 - The rapid growth of XML adoption has urged for the need of a proper representation for semi-structured documents, where the document structural information has to be taken into account so as to support more precise document analysis. In this paper, an XML document representation named "structured link vector model" is adopted, with a kernel matrix included for modeling the similarity between XML elements. Our formulation allows individual XML elements to have their own weighted contribution to the overall document similarity while at the same time allows the between-clement similarity to be captured. An iterative algorithm is derived to learn the kernel matrix. For performance evaluation, the ACM SIGMOD Record dataset as well as the CEDE dataset have been tested. Our proposed method outperforms significantly the traditional vector space model and the edit-distance based methods. In addition, the kernel matrix obtained as a by-product provides knowledge about the conceptual relationship between the XML elements.

AB - The rapid growth of XML adoption has urged for the need of a proper representation for semi-structured documents, where the document structural information has to be taken into account so as to support more precise document analysis. In this paper, an XML document representation named "structured link vector model" is adopted, with a kernel matrix included for modeling the similarity between XML elements. Our formulation allows individual XML elements to have their own weighted contribution to the overall document similarity while at the same time allows the between-clement similarity to be captured. An iterative algorithm is derived to learn the kernel matrix. For performance evaluation, the ACM SIGMOD Record dataset as well as the CEDE dataset have been tested. Our proposed method outperforms significantly the traditional vector space model and the edit-distance based methods. In addition, the kernel matrix obtained as a by-product provides knowledge about the conceptual relationship between the XML elements.

KW - Kernel

KW - XML

KW - Computer science

KW - Text analysis

KW - Information analysis

KW - Iterative algorithms

KW - Testing

KW - Fourier transforms

KW - Training data

UR - http://www.scopus.com/inward/record.url?scp=30944453296&partnerID=8YFLogxK

U2 - 10.1109/EEE.2005.87

DO - 10.1109/EEE.2005.87

M3 - Conference proceeding

AN - SCOPUS:30944453296

SN - 9780769522746

SN - 0769522742

T3 - Proceedings - IEEE International Conference on e-Technology, e-Commerce and e-Service

SP - 353

EP - 358

BT - Proceedings - 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05

PB - IEEE

T2 - 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, EEE-05

Y2 - 29 March 2005 through 1 April 2005

ER -

Learning the kernel matrix for XML document clustering

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this