atalwalkar

Good point. "c" is the column on which we want to perform n-gram extraction, and as you mentioned "n" is the number of n-grams while "k" is the number of...

Hi John, These are good points -- thanks for the feedback! -Ameet On Fri, Aug 30, 2013 at 11:59 AM, John Owens [email protected]: > "output a set of all “word1_word2”...

Sorry for the confusion. In summary, we first pick the top 1000 bigrams across the entire corpus of documents, and then for each document we compute the number of times...

Thanks for the feedback. I'll update the text accordingly. On Fri, Aug 30, 2013 at 12:16 PM, John Owens [email protected]: > Totally makes sense. Include that text directly! :) >...