Mixtures of Probabilistic PCAs and Fisher Kernels for Word and Document Modeling

Georges Siolas (1) , Florence d'Alché-Buc (1)

1 APA - Apprentissage et Acquisition des connaissances

We present a generative model for constructing continuous word representations using mixtures of probabilistic PCAs. Applied to co-occurrence data, the model performs word clustering and allows the visualization of each cluster in a reduced space. In combination with a simple document model, it permits the definition of low-dimensional Fisher scores which are used as document features. We investigate the models’ potential through kernel-based methods using the corresponding Fisher kernels.

Domaines: Informatique [cs]

Georges Siolas, Florence d'Alché-Buc. Mixtures of Probabilistic PCAs and Fisher Kernels for Word and Document Modeling. International Conference on Artificial Neural Networks - ICANN 2002, Aug 2002, Madrid, Spain. pp.769-774, ⟨10.1007/3-540-46084-5_125⟩. ⟨hal-01548185⟩