ICE 7 - slcc2c/CS5590_Python GitHub Wiki

In class exercise: In class, we further work on the tokenization, pos-tagging, entity extraction, biagram and trigram. For all the exercises import the right module from NLTK. You need to go through the slides to find them.

1. Define a paragraph of text includes three sentences
2. Use WordNet module to find the meaning of some words in your text
3. Apply Tokenization on the text
4. Apply Stemming on the text
5. Apply POS on the text
6. Apply Lemmatization on the text
7. Apply Trigram on the text
8. Apply Named Entity Recognition on the text

Code is here I could not get the NLTK downloader working on my Mac