Probabilistic Models in the Study of Language

I'm in the process of writing a textbook on the topic of using probabilistic models in scientific work on language ranging from experimental data analysis to corpus work to cognitive modeling. A current (partial) draft is available here. The intended audience is graduate students in linguistics, psychology, cognitive science, and computer science who are interested in using probabilistic models to study language. Feedback (both comments on existing drafts, and expressed desires for additional material to include!) is more than welcome -- send it to rlevy@ling.ucsd.edu.

Here are drafts of those individual chapters that are already available:

  1. Univariate Probability, with R code
  2. Multivariate Probability, with R code
  3. Parameter Estimation, with R code
  4. Confidence Intervals and Hypothesis Testing, with R code
  5. Generalized Linear Models
  6. Hierarchical Models (a.k.a. multi-level, mixed-effects models), with R code
  7. Latent-Variable Models
  8. Nonparametric Models
  9. Probabilistic Grammars

Appendices:

  1. More probability Distributions
  2. A brief introduction to directed graphical models
  3. A brief introduction to sampling techniques

Last modified: Thu Apr 9 18:20:17 PDT 2009