Combining Statistical Language Models via the Latent Maximum Entropy Principle

Latent Maximum Entropy Principle for Statistical Language Modeling

In this paper, w dcscrihe a unified probabilistic framework for statistical lmiguage modeling, latent mmmum mtmpy Wnciple. The salient feature of this approach is that the hidden causal hierarchical dependency structure can be enc d e d into thpsiatwtical model in a principled way hy mixturts of expoocntial families with a rirh expressive power. We first show tlie problem lormulatiun, whition, ...

Learning Mixture Models with the Latent Maximum Entropy Principle

We present a new approach to estimating mixture models based on a new inference principle we have proposed: the latent maximum entropy principle (LME). LME is different both from Jaynes’ maximum entropy principle and from standard maximum likelihood estimation. We demonstrate the LME principle by deriving new algorithms for mixture model estimation, and show how robust new variants of the EM al...

Boltzmann Machine Learning with the Latent Maximum Entropy Principle

We present a new statistical learning paradigm for Boltzmann machines based on a new inference principle we have pro­ posed: the latent maximum entropy principle (LME). LME is different both from Jaynes' maximum entropy principle and from stan­ dard maximum likelihood estimation. We demonstrate the LME principle by deriving new algorithms for Boltzmann machine pa­ rameter estimation, and show h...

Semantic n-gram language modeling with the latent maximum entropy principle

Compact Maximum Entropy Language Models

In language modeling we are always confronted with a sparse data problem. The Maximum Entropy formalism allows to fully integrate complementary statistical properties of limited corpora. The focus of the present paper is twofold. The new smoothing technique of LM-induced marginals is introduced and discussed. We then highlight the advantages resulting from a combination of robust features and s...