- Install [Python 2.7] (http://www.python.org/download/releases/2.7/)
- Install NLTK Library
- Download all available NLTK data
- Download 2-3 books from Project Gutenburg
- HTML: nltk.clean_html
- HTML: BeautifulSoup
- RSS: feedparser
- PDF: pypdf
- MS Word: pywin23
- [OpenWIMs Demo] (http://openwims.org/demo/)
- SLIDES: Discourses in Human Language
- SOURCE: [Discourses in Human Language] (https://github.com/bbengfort/discourses-in-language-processing)