Extract bigrams python

from nltk import word_tokenize 
from nltk.util import ngrams


text = ['cant railway station', 'citadel hotel', 'police stn']
for line in text:
    token = nltk.word_tokenize(line)
    bigram = list(ngrams(token, 2))

    # the '2' represents bigram...you can change it to get ngrams with different size

Source: stackoverflow.com

Similar codes

1 vote291 views1 answer
Python take input from terminal
Python
4 votes348 views1 answer
How to input multiple integers in python
Python
0 vote342 views1 answer
Run django using nssm
Python
12 votes324 views2 answers
How to read input from stdin in python
Python
0 vote335 views1 answer
[E053] Could not read config.cfg from C:\Users\hp\AppData\Local\Programs\Python\Python37\lib\site-packages\resume_parser\degree\model\config.cfg
Python
0 vote335 views1 answer
How to search a file in windows 10 using python
Python
0 vote336 views1 answer
What is *args and **kwargs in django
Python
0 vote332 views2 answers
Cron job python
Python
0 vote337 views1 answer
Which clause is used to place condition with GROUP BY clause in a table
Python
14 votes288 views6 answers
Ruby print
Python