de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Discovering a Term Taxonomy from Term Similarities Using Principal Component Analysis

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons44076

Bast,  Holger
Algorithms and Complexity, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons44356

Dupret,  Georges
Algorithms and Complexity, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons44972

Majumdar,  Debapriyo
Algorithms and Complexity, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Bast, H., Dupret, G., Majumdar, D., & Piwowarski, B. (2006). Discovering a Term Taxonomy from Term Similarities Using Principal Component Analysis. In Semantics, web and mining : Joint International Workshops, EWMF 2005 and KDO 2005 (pp. 103-120). Berlin, Germany: Springer.


Cite as: http://hdl.handle.net/11858/00-001M-0000-000F-2295-E
Abstract
We show that eigenvector decomposition can be used to extract a term taxonomy from a given collection of text documents. So far, methods based on eigenvector decomposition, such as latent semantic indexing (LSI) or principal component analysis (PCA), were only known to be useful for extracting symmetric relations between terms. We give a precise mathematical criterion for distinguishing between four kinds of relations of a given pair of terms of a given collection: unrelated (car - fruit), symmetrically related (car - automobile), asymmetrically related with the first term being more specific than the second (banana - fruit), and asymmetrically related in the other direction (fruit - banana). We give theoretical evidence for the soundness of our criterion, by showing that in a simplified mathematical model the criterion does the apparently right thing. We applied our scheme to the reconstruction of a selected part of the open directory project (ODP) hierarchy, with promising results.