We apply and discuss generalizable Gaussian mixture (GGM) models for text mining. The model automatically adapts model complexity for a given text representation. We show that the generalizability of these models depends on the dimensionality of the representation and the sample size. We discuss the relation between supervised and unsupervised learning in the test data. Finally, we implement a novelty detector based on the density model.
|Title of host publication||IEEE Procedings of Acoustics, Speech, and Signal Processing|
|Place of Publication||Istanbul, Turkey|
|Publication status||Published - 2000|
|Event||IEEE International Conference on Acoustics, Speech, and Signal Processing 1995 - Detroit, MI, United States|
Duration: 9 May 1995 → 12 May 1995
|Conference||IEEE International Conference on Acoustics, Speech, and Signal Processing 1995|
|Period||09/05/1995 → 12/05/1995|