I am getting a parsing error when I use the following code in Jupyter using python 3.4
import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer
train_text = state_union.raw("2005-GWBush.txt")
sample_text = state_union.raw("2006-GWBush.txt")
custom_sent_tokenizer = PunktSentenceTokenizer(train_text)
tokenized = custom_sent_tokenizer.tokenize(sample_text)
def process_content():
try:
for i in tokenized:
words = nltk.word_tokenize(i)
tagged = nltk.pos_tag(words)
chunkGram = r"""Chunk: {<RB.?>*<VB.?>*<NNP><NN>?}"""
chunkParser = nltk.RegexpParser(chunkGram)
chunked = chunkParser.parse(tagged)
print(chunked)
I am getting the following error:
File "<ipython-input-12-a049462ffecb>", line 26
^
SyntaxError: unexpected EOF while parsing
Please advise on how I can solve this parsing error