Syllabus
1. Introduction
2. Beta-Bernouli and Dirichlet-Categorial models
3. Modeling document collections, Categorical Mixture models, Expectation-Maximization
4. Gibbs Sampling, Latent Dirichlet allocation
5. Unsupervised Text Segmentation
6. Unsupervised tagging, Word alignment, Unsupervised parsing
7. K-means, Mixture of Gaussians, Hierarchical clustering, evaluation
8. T-SNE, Principal Component Analysis, Independent Component Analysis
9. Linguistic Interpretation of Neural Networks
Annotation
The goal of the course is to introduce basic methods of unsupervised machine learning and their applications in natural language processing. We will discuss methods like Bayesian inference, Expectation-Maximization, Cluster analysis, methods using neural networks and other currently used methods.
Selected applications will be discussed in detail and implemented at the lab sessions.