Passage retrieval revisited

  • Authors:
  • Marcin Kaszkiel;Justin Zobel

  • Affiliations:
  • Department of Computer Science, RMIT, GPO Box 2476V, Melbourne 3001, Australia;Department of Computer Science, RMIT, GPO Box 2476V, Melbourne 3001, Australia

  • Venue:
  • Proceedings of the 20th annual international ACM SIGIR conference on Research and development in information retrieval
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

Ranking based on passages addresses some of the shortcomings ofwhole-document ranking. It provides convenient units of text toreturn to the user, avoids the difficulties of comparing documentsof different length, and enables identification of short blocks ofrelevant material amongst otherwise irrelevant text. In this paperwe explore the potential of passage retrieval, based on anexperimental evaluation of the ability of passages to identifyrelevant documents. We compare our scheme of arbitrary passageretrieval to several other document retrieval and passage retrievalmethods; we show experimentally that, compared to these methods,ranking via fixed-length passages is robust and effective. Ourexperiments also show that, compared to whole-document ranking,ranking via fixed-length arbitrary passages significantly improvesretrieval effectiveness, by 8% for TREC disks 2 and 4 and by18%-37% for the Federal Register collection.