i am trying to make a biagram table from a corpus with a text file which contains 100 sentences but i am unable to do it. right now i only have code with showing how many sentences that text file has. I am new to machine translation and couldnt work it out from NLTK packages. Can anyone help? thanks
from nltk.corpus.reader import WordListCorpusReader
reader = nltk.corpus.PlaintextCorpusReader('.', ['100sentence.txt'])
print ("The number of sentences =", len(reader.sents()))
basically what i want to do is make a biagram table from my txt file and being able to count words that i want from the text file