This is a Convolutional Neural Network (CNN) we implemented to participate in the shared task Discriminating between Similar Languages (DSL) that was organized as part of the VarDial workshop at EACL'17.
Our experiments are described in the paper Discriminating between Similar Languages with Word-level Convolutional Neural Networks.
This model was trained and evaluated on the DSL Corpus Collection (DSLCC) v4.0, which is available at: http://ttg.uni-saarland.de/resources/DSLCC/