This is the full system. Train your part of speech taggers, unknown word guessers, NP-chunkers, dialogue act taggers, etc. using this tool. This is a standalone binary version. Also contains the full source code for the system.
This is a light version of the system. Motivation is mainly pedagogical.
Once you have learned a sequence of rules, you probably want to apply them to new text.
By means of this rule compiler, you can build a simple and flexible (but slow) tagger.
This is an alternative and more interesting way of using a sequence of replacement rules. Even slower, but much more flexible!
This is an example of how a sequence of replacement rules can be compiled into a Java program, forming a part of speech tagger for English.
It turns out that sequence of replacement rules can be interpreted in a way that makes the resulting tagger highly incremental. Good if you want to use a tagger in a dialogue system frontend.