@article{3022,
  author = {Chiyu Zhang, Muhammad Abdul-Mageed},
  title = {A Pre-trained BERT Model for Arabic Author Profiling},
  journal = {Journal of E - Technology},
  year = {2020},
  volume = {11},
  number = {2},
  doi = {https://doi.org/10.6025/jet/2020/11/2/54-59},
  url = {http://www.dline.info/jet/fulltext/v11n2/jetv11n2_2.pdf},
  abstract = {We report our models for detecting age, language variety, and gender from social media data in the context of the
Arabic author profiling and deception detection shared task (APDA) [32].We build simple models based on pre-trained
bidirectional encoders from transformers (BERT). We first fine-tune the pre-trained BERT model on each of the three datasets
with shared task released data. Then we augment shared task data with in-house data for gender and dialect, showing the
utility of augmenting training data. Our best models on the shared task test data are acquired with a majority voting of various
BERT models trained under different data conditions. We acquire 54.72% accuracy for age, 93.75% for dialect, 81.67% for
gender, and 40.97% joint accuracy across the three tasks.1},
}