A Simple Method for Estimating Term Mutual Information

Article English OPEN
Cai, Di; McCluskey, Thomas L.;
  • Publisher: Journal of Computing
  • Subject: Q1

The ability to formally analyze and automatically measure statistical dependence of terms is a core problem in many areas of science. One of the commonly used tools for this is the expected mutual information (MI) measure. However, it seems\ud that MI methods have not a... View more
  • References (4)

    M. Ait Kerrou m, A. H am mou ch, and D. Aboutajd ine, “Textu ral featu re selection by joint m u tual inform ation based on gau ssian m ixtu re m od el for m u ltisp ectral im age classification,” Pattern Recognition Letters, vol 3, no. 10, pp . 1168-1174, 2010.

    [2] A. E. Akad i, A.E. Abd eljalil El Ou ard ighi, and D. Abou tajd ine, “A pow erfu l featu re selection ap p roach based on m u tu al inform ation,” International Journal of Computer Science and N etwork Security, vol. 8, p p . 116-121, 2008.

    for Information Science, vol. 16, no. 1, p p. 22-29, 1990.

    [6] H . Fang and C. X. Zhai, “Semantic term m atching in axiom atic [7] S. Gau ch, J. Wang, and S. M. Rachakond a, “A corp u s analysis [10] H .-W. Liu , J.-G. Su n, L. Liu , and H .-J. Zhang, “Featu re selection [11] R. M. Losee, Jr., “Term d ep end ence: A basis for Lu hn and Zip f [13] R. Mand ala, T. Toku naga, and H . Tanaka, “Qu ery exp ansion [17] G. Wang, F.H . Lochovsky, and Q. Yang, “Featu re selection w ith m u tu al

  • Metrics
Share - Bookmark