Skip to content


Subversion checkout URL

You can clone with
Download ZIP
For patches to NLTK
Python Emacs Lisp Other
Pull request Compare This branch is 2361 commits behind nltk:develop.
Failed to load latest commit information.
emacs Some print statements made functions
examples updated copyright year range; fixed my email address
javasrc updated copyright year range; fixed my email address
nltk Revert "precompiling word tokenizer"
papers updated copyright year range; fixed my email address
tools updated copyright year range; fixed my email address
web added howto link
.gitattributes Introduce end-of-line normalization
.gitignore removed .orig file generaged by mergetools and added *.orig files to …
ChangeLog finalise changelog for next release
INSTALL.txt new installation URL
LICENSE.txt updated copyright year range; fixed my email address pull fixes to setuptools, cf nltk#437
Makefile updated print function
NOTICE.txt updated copyright year range; fixed my email address updated contributors
README.txt updated copyright year range; fixed my email address
RELEASE-HOWTO fix instructions about tags
jenkins-job-config.xml fixed issues with coverage and pylint results added files and fixed tox.ini for jenkins setup
pip-req.txt added files and fixed tox.ini for jenkins setup
setup.cfg updates to support building 2.0.1rc2 pull fixes to setuptools, cf nltk#437
tox.ini Testing: don't install svmlight in Python 3.3 environment

Natural Language Toolkit (NLTK)

NLTK -- the Natural Language Toolkit -- is a suite of open source Python modules, data sets and tutorials supporting research and development in Natural Language Processing.

Copyright (C) 2001-2013 NLTK Project

For license information, see LICENSE.txt

For documentation, please visit


NLTK source code is distributed under the Apache 2.0 License.
NLTK documentation is distributed under the Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States license.
NLTK corpora are provided under the terms given in the README file for each corpus; all are redistributable, and available for non-commercial use.
NLTK may be freely redistributed, subject to the provisions of these licenses.



If you would like to contribute to NLTK, please post your ideas to nltk-dev, or fork nltk on github.

The following people have contributed to NLTK:

Rami Al-Rfou', Mark Amery, Greg Aumann, Yonatan Becker, Paul Bedaride, Steven Bethard, Robert Berwick, Dan Blanchard, Nathan Bodenstab, Francis Bond, Paul Bone, Jordan Boyd-Graber, Daniel Blanchard, Phil Blunsom, Lars Buitinck, Steve Cassidy, Chen-Fu Chiang, Dmitry Chichkov, Jinyoung Choi, Andrew Clausen, Lucas Champollion, Trevor Cohn, David Coles, Lucas Cooper, Robin Cooper, Chris Crowner, James Curran, Dariel Dato-on, Selina Dennis, Leon Derczynski, Alexis Dimitriadis, Nikhil Dinesh, Liang Dong, David Doukhan, Rebecca Dridan, Pablo Duboue, Christian Federmann, Michelle Fullwood, Dan Garrette, Jean Mark Gawron, Sumukh Ghodke, Yoav Goldberg, Dougal Graham, Brent Gray, Simon Greenhill, Eduardo Pereira Habkost, Masato Hagiwara, Michael Hansen, Yurie Hara, Will Hardy, Tyler Hartley, Peter Hawkins, Michael Heilman, Bruce Hill, Amy Holland, Kristy Hollingshead, Baden Hughes, Rebecca Ingram, Edward Ivanovic, Thomas Jakobsen, Piotr Kasprzyk, Angelos Katharopoulos, Sudharshan Kaushik, Chris Koenig, Mikhail Korobov, Stefano Lattarini, Pierre-François Laquerre, Stefano Lattarini, Haejoong Lee, Max Leonov, Tom Lippincott, Peter Ljunglöf, Nitin Madnani, Bjørn Mæland, Christopher Maloof, Rob Malouf, Iker Manterola, Carl de Marcken, Mitch Marcus, Torsten Marek, Robert Marshall, Duncan McGreggor, Xinfan Meng, Margaret Mitchell, Tomonori Nagano, Jason Narad, Morten Neergaard, David Nemeskey, Eric Nichols, Joel Nothman, Ted Pedersen, Jacob Perkins, Alberto Planas, Alessandro Presta, Martin Thorsen Ranang, Brandon Rhodes, Joshua Ritterman, Will Roberts, Stuart Robinson, Carlos Rodriguez, Alex Rudnick, Jussi Salmela, Geoffrey Sampson, Kepa Sarasola, Kevin Scannell, Nathan Schneider, Rico Sennrich, Thomas Skardal, Eric Smith, Rob Speer, Peter Spiller, Richard Sproat, Ceri Stagg, Peter Stahl, Oliver Steele, Jan Strunk, Claire Taylor, Steven Tomcavage, Tiago Tresoldi, Petro Verkhogliad, Peter Wang, Charlotte Wilson, Steven Xu, Beracah Yankama, Patrick Ye, Jason Yoder.

Something went wrong with that request. Please try again.