Classifying ASR Transcriptions According to Arabic Dialect

We describe several systems for identifying short samples of Arabic dialects, which were prepared for the shared task of the 2016 DSL Workshop (Malmasi et al., 2016). Our best system, an SVM using character tri-gram features, achieved an accuracy on the test data for the task of 0.4279, compared to a baseline of 0.20 for chance guesses or 0.2279 if we had always chosen the same most frequent class in the test set. This compares with the results of the team with the best weighted F1 score, which was an accuracy of 0.5117. The team entries seem to fall into cohorts, with the all the teams in a cohort within a standard-deviation of each other, and our three entries are in the third cohort, which is about seven standard deviations from the top.