This is a response to my mail from Stephen Byrd, one of the authors of the NLTK book:
NLTK can work for parsing the Dutch language if you provide grammar rules. Consult the NLTK book: http://www.nltk.org/book You may be able to use the Alpino package for development (or for preparing a statistical analyzer). If your main interest gets parsed Dutch proposals, I recommend that you try to find an existing parser, rather than developing your own.
In the end, I ended up using Alpino parsing, which is really strong and written in Prolog, but I managed to port (binary version) in python.
source
share