The efficiency of inverted index and cluster searches

ABSTRACT

The processing time and disk space requirements of an inverted index and top-down cluster search are compared. The cluster search is shown to use both more time and more disk space, mostly due to the large number of cluster centroids needed by the search. When shorter centroids are used, the efficiency of the cluster search improves, but the inverted index search remains more efficient.

REFERENCES

• BUCK85: Chris Buckley , Alan F. Lewit, Optimization of inverted vector searches, Proceedings of the 8th annual international ACM SIGIR conference on Research and development in information retrieval, p.97-110, June 05-07, 1985, Montreal, Quebec, Canada [doi>10.1145/253495.253515]
• FOX83: Fox, E. A., "Characterization of Two New Experimental Collections in Computer and Information Science Containing Textual and Bibliographic Concepts", Technical report 83-560, Department of Computer Science, Cornell University, September 1983.
• GRIF84: Griffiths, A., Robinson, L. A., Willett, P., "Hierarchic Agglomerative Clustering Methods for Automatic Document Classification", The Journal of Documentation XL(3):175-205,1984.
• GRIF85: Griffiths, A., Luckhurst, H. C., Willett, P., "Using Interdocument Similarity Information in Document Retrieval Systems", Journal of the American Society for Information Science XXXVII(1):3-11, 1986.
• JARD71: Jardine, N., van Rijsbergen, C. J., #Phe Use of Hierarchic Clustering in Information Retrieval", Information Storage and Retrieval VII(5):217- 240, 1971.
• SMAR71: G. Salton, The SMART Retrieval System—Experiments in Automatic Document Processing, Prentice-Hall, Inc., Upper Saddle River, NJ, 1971
• VOOR86: Ellen Marie Voorhees, The effectiveness and efficiency of agglomerative hierarchic clustering in document retrieval, Cornell University, Ithaca, NY, 1986