An N-gram is an ordered collection of N elements of the same kind, usually presented in a large collection of many other similar N-grams
A word is a single distinct meaningful element of a data
"It has support for tokenizing lemmatizing n-gram ideas that span more than one words"
from question "Find course name using nltk and python"
"If you will be classifying multi-paragraph text all in one language a functional words list which your bag of words with pruning of hapaxes will quickly approximate might well serve you perfectly and could work better than n-gram"
from question "Selecting suitable model for creating Language Identification tool"
"For some problems character level n-gram do better than words level and logistic regression parameters"
from question "How to increase the presicion of text classification with the RBM?"