The python libraries (and their licenses) that we are explicitly depending on,
are the following ones,

    - nltk (Apache License)
    - numpy (BSD)
    - scipy (BSD)
    - scikit-learn (BSD)
    - mock (BSD)
    - docopt (MIT)
    - future (MIT)
    - appdirs (MIT)
    - wget (Public Domain)
    - colorama (BSD)
    - featureforge (BSD)

The development tools we are using:

    - nose (LGPL)
    - factory-boy (MIT)

Additionally, in order to be able to create your own iepy-ready corpus with our
preprocessing tools, you'll need to download the following things that are not
provided by this software

    - punkt tokenizer (acquirable with the NLTK downloader or the
                       download_third_party_data script)
    - wordnet (acquirable with the NLTK downloader or the
               download_third_party_data script)
    - GPL Stanford CoreNLP (acquirable with download_third_party_data script)
    - GPL Stanford Spanish Models (acquirable with download_third_party_data script)