Hello I am a student working in the area of text mining. I want to generate N-gram frequency profile for a document. But I don't want word N-grams, I mean to say that, suppose the text contains " my name is joe" then the N-gram freq profile must consist of all the 2-grams(say n=2) such as my, na, am, me, is, jo, oe. that is for every token in the text, 2-grams must be displayed along with their frequencies. What NSP is doing is that, it is generating the word n-grams like "my name", "name is"...etc. Kindly help me out to get the desired profile for a document.
Thanks & Regards, Santosh Kumar Paluri "Salvation lies within" ____________________________________________________________________________________ Never miss an email again! Yahoo! Toolbar alerts you the instant new Mail arrives. http://tools.search.yahoo.com/toolbar/features/mail/