gistfile1.py

from nltk import pos_tag
from sussex_nltk import lemmatize_tagged
from nltk.tag import untag

#Example list of words
words = ['The', 'badgers', 'were', 'eating', 'some', 'berries', 'and', 'jam']

#PoS tag the words
tagged_words = pos_tag(words)

#Lemmatise the words
lemma_words = [lemmatize_tagged(word) for word in t]

#Remove the PoS tags in order to use the lemmas as features
features = untag(lemma_words)

print features