This tutorial is meant to demonstrate how to use many of the basic options of SNoW. We show how to start with training examples, train a classifier, and then test the classifier with some more examples. The example task given is context-sensitive spelling correction [Golding and Roth, 1999]. The task is to train a classifier with many examples of the correct usage of the words ``their'' and ``there'' so that, given a test context, the classifier can decide which word best fits the context.
A script demonstrating some of the topics discussed here is included in the tutorial/ subdirectory of the software distribution called tutorial.sh. It can easily be modified and used as a general purpose SNoW script.