This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# coding=UTF-8 | |
import nltk | |
from nltk.corpus import brown | |
# This is a fast and simple noun phrase extractor (based on NLTK) | |
# Feel free to use it, just keep a link back to this post | |
# http://thetokenizer.com/2013/05/09/efficient-way-to-extract-the-main-topics-of-a-sentence/ | |
# Create by Shlomi Babluki | |
# May, 2013 |