XLike Language Identifier




This language identification web service takes as the input parameter the free text in utf8 encoding and outputs the language code following the ISO 639-2 specification. This service is based on the well-known method that uses character-based n-gram language models for each target language. It has been developed within the FP7 project XLike (www.xlike.org) and covers the languages processed within this project (en, es, de, ca, sl, zh, hr).

You don’t have the permission to edit this resource.