No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects
Chiyu Zhang, Muhammad Abdul-Mageed · 2019
We present our deep leaning system submitted to MADAR shared task 2 focused on twitter user dialect identification.We develop tweetlevel identification models based on GRUs and BERT in supervised and semi-supervised settings.We then introduce a simple, yet effective, method of porting tweet-level labels at the level of users.Our system ranks top 1 in the competition, with 71.70% macro F 1 score and 77.40% accuracy.