NLTK — the Natural Language Toolkit — is a suite of open source Python modules, data and documentation for research and development in natural language processing. NLTK contains Code supporting dozens of NLP tasks, along with 40 popular Corpora and extensive Documentation including a 375-page online Book. Distributions for Windows, Mac OSX and Linux are available.
M. Sanderson. Proc. of the Seventeenth Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, page 142-151. (1994)
K. VanLehn, S. Siler, C. Murray, and W. Baggett. Proc. of the Twenth-first Annual Conference of the Cognitive Science Society, Hillsdale, NJ, Erlbaum, (1998)To be published?.