English

KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT

Computation and Language 2020-05-19 v1 Machine Learning

Abstract

This research presents our team KEIS@JUST participation at SemEval-2020 Task 12 which represents shared task on multilingual offensive language. We participated in all the provided languages for all subtasks except sub-task-A for the English language. Two main approaches have been developed the first is performed to tackle both languages Arabic and English, a weighted ensemble consists of Bi-GRU and CNN followed by Gaussian noise and global pooling layer multiplied by weights to improve the overall performance. The second is performed for other languages, a transfer learning from BERT beside the recurrent neural networks such as Bi-LSTM and Bi-GRU followed by a global average pooling layer. Word embedding and contextual embedding have been used as features, moreover, data augmentation has been used only for the Arabic language.

Keywords

Cite

@article{arxiv.2005.07820,
  title  = {KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT},
  author = {Saja Khaled Tawalbeh and Mahmoud Hammad and Mohammad AL-Smadi},
  journal= {arXiv preprint arXiv:2005.07820},
  year   = {2020}
}

Comments

8 pages without references, 4 figures, SemEval 2020 conference