Research Area:  Machine Learning
This paper presents the ArabicProcessors teams system designed for sarcasm (subtask 1) and sentiment (subtask 2) detection shared task. We created a hybrid system by combining rule-based features and both static and dynamic embeddings using transformers and deep learning. The system-s architecture is an ensemble of Naive bayes, MarBERT and Mazajak embedding. This process scored an F1-score of 51 percent on sarcasm and 71 percent for sentiment detection.
Keywords:  
Author(s) Name:  Kamel Gaanoun, Imade Benelallam
Journal name:  Natural Language Processing
Conferrence name:  
Publisher name:  ACN
DOI:  
Volume Information:  
Paper Link:   https://aclanthology.org/2021.wanlp-1.45/