Extracting Events using Nltk
stop_words = set(stopwords.words('english'))
print(stop_words )
ne_1 = word_tokenize(sample)
filtered_sentence = [w for w in ne_1 if not w in stop_words]
filtered_sentence = []
for w in ne_1:
if w not in stop_words:
filtered_sentence.append(w)
filtered_sentence
# ne_tree = ne_chunk(pos_tag(word_tokenize(sample)))
ne_2 = pos_tag(filtered_sentence)
ne_2
ne_3 = ne_chunk(ne_2)
ne_3
When I run this it detects States like Texas as an Organizations, dont know why.
Eg: "There is a Python Conference at the cafe in Texas on 1/6/2017 "
My main Goal
I am trying to extract a date related to the event.
Output required:
Python Conference 1/6/2017 Cafe Texas
You must be logged in to post. Please login or register an account.