YFilter at TREC-9

Abstract

We built a filtering system YFILTER this year, which we used for experiments on profile updating and thresholds setting. Our focus is using incremental Rocchio for introducing new query terms and term weighting. Although 1, 0.5, 0.25 is a widely used Rocchio ratio for query expansion based on relevance feedback, we found that the optimal setting for information filtering is corpus and profile dependent. In addition to a new Rocchio ratio, we tested a modified idf measure for term weighting (ydf) that is biased towards words with middle range term frequency.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2000
Accession Number
ADA456317

Entities

People

  • Jamie Callan
  • Yi Zhang

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Classification
  • Computer Science
  • Engineering
  • Feedback
  • Filtration
  • Frequency
  • Information Retrieval
  • Language
  • Learning
  • Machine Learning
  • Natural Languages
  • Precision

Readers

  • Information Retrieval
  • Regression Analysis.