Basic Statistics Concepts
This lecture summarizes basic terminology and concepts in statistics and probabilities and how they can
be applied to model a specific linguistic task: parts of speech tagging.
Please refer to the following notes from this course:
Statistical Methods for NLP, Goteborg's University:
- Probability Theory
- Random Variables
- Information Theory
- Statistical Inference
- Markov Models
- Parts of Speech Tagging: Statistical Models
Other excellent tutorials on Machine Learning are available in repository of tutorials
by Andrew Moore (Carnegie Mellon University) (also available here.
In particular, read:
- Probabilistic and Bayesian Analytics
- Cross-validation for detecting and preventing overfitting
Last modified March 7th, 2011