Topic Hierarchy Generation via Linear Discriminant Projection

Tao Li, Shenghuo Zhu, Mitsunori Ogihara

Research output: Contribution to journalArticle

12 Scopus citations

Abstract

Automatic hierarchy generation using linear discriminant projection approach is presented. The approach measures the similarities between categories by the distances between category centroids in the transformed space. A hierarchical clustering method is used to generate the dendogram based on the similarity measures. The experiments demonstrate that generated hierarchies can improve classification performance on most datasets.

Original languageEnglish (US)
Pages (from-to)421-422
Number of pages2
JournalSIGIR Forum (ACM Special Interest Group on Information Retrieval)
Issue numberSPEC. ISS.
StatePublished - 2003
Externally publishedYes

    Fingerprint

Keywords

  • Clustering
  • Hierarchy
  • Text Categorization

ASJC Scopus subject areas

  • Hardware and Architecture
  • Management Information Systems

Cite this