NLTK Home

Open source Python modules, linguistic data and documentation for research and development in natural language processing and text analytics, with distributions for Windows, Mac OSX and Linux.

• News - NLTK Cookbook by Jacob Perkins [December 2010], NLTK book in third printing [November 2010], Japanese translation of NLTK book published [November 2010], Version 2.0b9 released [July 2010], Version 2.0b8 included in Ubuntu 10.4 [February 2010]
• Code - functionality provided by NLTK in over 100,000 lines of Python code, distributed under the Apache License
  
• Data - ~60 corpora, grammar collections, and trained models that come with NLTK
• Quotes - what people have said about NLTK

Getting Started

• Documentation - book, articles, guides, reviews
• Download - instructions for downloading and installing Python and NLTK on all platforms
• Getting Started - simple things to try, including NLTK's demonstrations
• Subscribe - sign up for important announcements - approx 1 post per month

Getting Help

• FAQ - answers to frequently asked questions
• HOWTO - guides for a variety of NLTK packages, including many examples
• User forum - mailing list for discussion amongst NLTK users
• Chatroom - #nltk on irc.freenode.net (not often staffed)
  

Software

• API Documentation - complete documentation of all NLTK modules
• Source - browse the Python source code
• Google Code - the home of the NLTK development work (submit a feature request or bug report)
• People - the NLTK development team

Education and Research

• Courses - ~100 courses in 23 countries using NLTK (artificial intelligence, computational linguistics, information retrieval, machine learning)
• Projects - ideas for student projects
• Teaching - information for instructors teaching courses using NLTK
• Research - hundreds of research papers that mention or use NLTK, via Google Scholar