A 'Gibbs-Newton' Technique for Enhanced Inference of Multivariate Polya Parameters and Topic Models.
Osama KhalifaDavid Wolfe CorneMike J. ChantlerPublished in: CoRR (2015)
Keyphrases
- topic models
- gibbs sampling
- collapsed gibbs sampling
- variational inference
- topic modeling
- latent dirichlet allocation
- probabilistic model
- variational bayesian inference
- parameter estimation
- text mining
- markov chain monte carlo
- latent topics
- expectation maximization
- regression model
- text documents
- latent variables
- generative model
- maximum likelihood
- markov random field
- co occurrence
- pitman yor process
- parameter learning
- latent topic models
- text corpora
- relevance model
- semi supervised
- bayesian networks
- artificial intelligence