Improve precategorized collection retrieval by using supervised term weighting schemes

Ying Zhao, George Karypis

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

5 Scopus citations

Abstract

The emergence of the World Wide Web has led to an increased interest in methods for searching for information. A key characteristic of many online document collections is that the documents have pre-defined category information, such as the variety of scientific articles accessible via digital libraries (e.g. ACM, IEEE, etc.), medical articles, news-wires and various directories (e.g. Yahoo, OpenDirectory Project, etc.). However, most previous information retrieval systems have not taken the pre-existing category information into account. In this paper, we present weight adjustment schemes based upon the category information in the vector-space model, which are able to select the most content-specific and discriminating features. Our experimental results on TREC data sets show that the pre-existing category information does provide additional beneficial information to improve retrieval. The proposed weight adjustment schemes perform better than the vector-space model with the inverse document frequency (IDF) weighting scheme when queries are less specific. The proposed weighting schemes can also benefit retrieval when clusters are used as an approximations to categories.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Information Technology
Subtitle of host publicationCoding and Computing, ITCC 2002
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages16-21
Number of pages6
ISBN (Electronic)0769515061, 9780769515069
DOIs
StatePublished - 2002
EventInternational Conference on Information Technology: Coding and Computing, ITCC 2002 - Las Vegas, United States
Duration: Apr 8 2002Apr 10 2002

Publication series

NameProceedings - International Conference on Information Technology: Coding and Computing, ITCC 2002

Other

OtherInternational Conference on Information Technology: Coding and Computing, ITCC 2002
Country/TerritoryUnited States
CityLas Vegas
Period4/8/024/10/02

Bibliographical note

Publisher Copyright:
© 2002 IEEE.

Keywords

  • Computer science
  • Contracts
  • Frequency
  • Indexing
  • Information retrieval
  • Inverse problems
  • Software libraries
  • Text categorization
  • Text mining
  • US Department of Energy

Fingerprint

Dive into the research topics of 'Improve precategorized collection retrieval by using supervised term weighting schemes'. Together they form a unique fingerprint.

Cite this