German Dialect Identification Using Classifier Ensembles
This work addresses dialect identification for Swiss-German, but it is incremental as it applies existing ensemble methods to a specific dataset.
The paper tackled German dialect identification by developing an SVM classifier ensemble system trained on speech transcripts of five Swiss-German dialects, achieving a 62.03% F1-score and ranking third out of eight teams in a shared task.
In this paper we present the GDI_classification entry to the second German Dialect Identification (GDI) shared task organized within the scope of the VarDial Evaluation Campaign 2018. We present a system based on SVM classifier ensembles trained on characters and words. The system was trained on a collection of speech transcripts of five Swiss-German dialects provided by the organizers. The transcripts included in the dataset contained speakers from Basel, Bern, Lucerne, and Zurich. Our entry in the challenge reached 62.03% F1-score and was ranked third out of eight teams.