KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- May 2020
- DOI:
- 10.48550/arXiv.2005.07820
- arXiv:
- arXiv:2005.07820
- Bibcode:
- 2020arXiv200507820K
- Keywords:
-
- Computer Science - Computation and Language;
- Computer Science - Machine Learning
- E-Print:
- 8 pages without references, 4 figures, SemEval 2020 conference