> > I am working on a program that is written in Python 2.7 to be compatible > with the POS tagger that I import from Pattern. The tagger identifies all > the nouns in a text. I need to exclude from the tagger any text that is > within quotation marks, and also any word that begins with an upper case > letter (including words at the beginning of sentences). > > Any advice on coding that would be gratefully received. Thanks. >
Perhaps overkill, but wanted to make sure you knew about the Natural Language Toolkit: http://www.nltk.org/. -- https://mail.python.org/mailman/listinfo/python-list
