Getting condiitonal probability of n-gram using nltk

Asked Jun 25 '16 at 09:29

Active Jun 25 '16 at 09:52

Viewed 789 times

The N-gram model provides the probability of next word P(W) by seeing the history. (as per window size). How can I implement this in python using nltk?

Is there any pre-built package for the same?

I referred to this question.. However I am not able to import Ngram model. It gives me error as,

NameError: name 'NgramModel' is not defined

How can I solve this problem?

Edit - It seems that the NgramModel has been removed due to some bugs. Refer this. So which alternate model can be used?

edited May 23 '17 at 11:58

Community

asked Jun 25 '16 at 09:29

Riken Shah

3,022
5
29
56

Possible duplicate of [nltk language model (ngram) calculate the prob of a word from context](http://stackoverflow.com/questions/6462709/nltk-language-model-ngram-calculate-the-prob-of-a-word-from-context) – juanpa.arrivillaga Jun 25 '16 at 09:35
What was your import statement? – juanpa.arrivillaga Jun 25 '16 at 09:42
I tried `from nltk.corpus import NgramModel` and `from nltk import NgramModel` – Riken Shah Jun 25 '16 at 09:44
I also tried `from nltk.model import NgramModel` but it says `No module named model` – Riken Shah Jun 25 '16 at 09:46
Aha, it seems that the module has been removed pending some issues. https://groups.google.com/forum/#!topic/nltk-users/XdVKlhJ46nM – juanpa.arrivillaga Jun 25 '16 at 09:53

Getting condiitonal probability of n-gram using nltk

0 Answers0