This repository contains the programs used in the experiments we performed for participating in the DSL shared task 2016. The models and experiments are described in the follwing paper:

Çöltekin, Çağrı and Taraka Rama (2016). “Discriminating similar languages: experiments with linear SVMs and neural networks.” In: Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects. Osaka, Japan, (to appear).

Bibtex:

@inproceedings{coltekin-rama2016dsl,
  title = {Discriminating similar languages: experiments with linear {SVM}s and neural networks},
  author = {\c{C}\"{o}ltekin, \c{C}a\u{g}r\i{} and Rama, Taraka},
  date = {2016},
  booktitle = {Proceedings of the Third Workshop on {NLP} for Similar Languages, Varieties and Dialects},
  pages = {(to appear)},
  location = {Osaka, Japan},
}

All programs are written in python, require scikit-learn and/or Keras. The latest version can be found at https://github.com/coltekin/dsl2016-source. Please do not hesistate contact us if you have any questions.