Java Language Detection library.

This library uses a Naive Bayes classifier on n-grams of a text, with n ranging from 2 to 4.

This algorithms first needs to extract the n-grams repartition on a set of known documents (training phase) and then can reuse these results to detect the language of a unknown documents (detection phase).

This software is released under the Apache LICENSE 2.0. See the LICENSE file for more details.