We have now read and discussed the tutorials on NLTK basics and probability. If you haven't done so already, it would be to your benefit to use the Python interpreter in interactive mode, and satisfy yourself that you understand all the examples in the tutorials.
The NLTK package is installed in /afs/cs.pitt.edu/projects/nltk. You should be able to run it from unixs.cis.pitt.edu by adding /afs/cs.pitt.edu/projects/nltk/bin to your search path. Depending on your shell, for example, say "setenv PATH /afs/cs.pitt.edu/projects/nltk/bin:${PATH}" You can also just change this in your profile, so you won't have to do this every time you login. Or, you can just do ln -s /afs/cs.pitt.edu/projects/nltk/bin/python.
The goal of this assignment is both to learn how to use NLTK, and to learn how to run some interesting NLP experiments on a real text corpus.
The following exercises will be graded both for correctness, and for well-structured and well-documented code.