Open source Python modules, linguistic data and documentation for research and
development in natural language processing, supporting dozens of NLP tasks,
with distributions for Windows, Mac OSX and Linux.

As of version 3.5, python 2.7 is no longer supported and python3 is now
required.

NLTK comes with many corpora, toy grammars, trained models, etc. A complete
list is posted at: http://nltk.org/nltk_data/.  To retrieve all the data, use
"python3 -m nltk.downloader all". To ensure system wideinstallation, you can
run the command "python3 -m nltk.downloader -d /usr/share/nltk_data all" as
root. Note that the 'regex' package, also available on SBo, is required to run
this command.