Document Type
Conference Proceeding
Publication Date
2001
Abstract
We describe a unified probabilistic framework for statistical language modeling, the latent maximum entropy principle. The salient feature of this approach is that the hidden causal hierarchical dependency structure can be encoded into the statistical model in a principled way by mixtures of exponential families with a rich expressive power. We first show the problem formulation, solution, and certain convergence properties. We then describe how to use this machine learning technique to model various aspects of natural language, such as syntactic structure of sentences, semantic information in a document. Finally, we draw a conclusion and point out future research directions.
Repository Citation
Wang, S.,
Rosenfeld, R.,
& Zhao, Y.
(2001). Latent Maximum Entropy Principle for Statistical Language Modeling. IEEE Workshop on Automatic Speech Recognition and Understanding, 182-185.
https://corescholar.libraries.wright.edu/knoesis/281
Included in
Bioinformatics Commons, Communication Technology and New Media Commons, Databases and Information Systems Commons, OS and Networks Commons, Science and Technology Studies Commons
Comments
This paper was presented at the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) in 2001.