Text classification algorithms which are not Naive?

Question

Naive Bayes Algorithm assumes independence among features. What are some text classification algorithms which are not Naive i.e. do not assume independence among it's features.

Answer 1

The answer will be very straight forward, since nearly every classifier (besides Naive Bayes) is not naive. Features independence is very rare assumption, and is not taken by (among huge list of others):

• logistic regression (in NLP community known as maximum entropy model)
• linear discriminant analysis (fischer linear discriminant)
• kNN
• support vector machines
• decision trees / random forests
• neural nets
• ...

You are asking about text classification, but there is nothing really special about text, and you can use any existing classifier for such data.