Overview of the DSL Shared Task 2015
Marcos Zampieri, Liling Tan, Nikola Ljube, Preslav Nakov · 2015
We present the results of the 2nd edition of the Discriminating between Similar Lan-guages (DSL) shared task, which was or-ganized as part of the LT4VarDial’2015 workshop and focused on the identifica-tion of very similar languages and lan-guage varieties. Unlike in the 2014 edi-tion, in 2015 we had an Others category with languages that were not seen on train-ing. Moreover, we had two test datasets: one using the original texts (test set A), and one with named entities replaced by placeholders (test set B). Ten teams partic-ipated in the task, and the best-performing system achieved 95.54 % average accuracy on test set A, and 94.01 % on test set B. 1