Abstract
This paper describes the system used in SemEval-2022 Task 6: Intended Sarcasm Detection in English and Arabic. Achieving 20th,3rd places with 34& 47 F1-Sarcastic score for task A, 16th place for task B with 0.0560 F1-macro score, and 10, 6th places for task C with72% and 80% accuracy on the leaderboard. A voting classifier between either multiple different BERT-based models or machine learningmodels is proposed, as our final model. Multiple key points has been extensively examined to overcome the problem of the unbalance ofthe dataset as: type of models, suitable architecture, augmentation, loss function, etc. In addition to that, we present an analysis of ourresults in this work, highlighting its strengths and shortcomings.- Anthology ID:
- 2022.semeval-1.126
- Volume:
- Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 896–906
- Language:
- URL:
- https://aclanthology.org/2022.semeval-1.126
- DOI:
- 10.18653/v1/2022.semeval-1.126
- Cite (ACL):
- Reem Abdel-Salam. 2022. reamtchka at SemEval-2022 Task 6: Investigating the effect of different loss functions for Sarcasm detection for unbalanced datasets. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 896–906, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- reamtchka at SemEval-2022 Task 6: Investigating the effect of different loss functions for Sarcasm detection for unbalanced datasets (Abdel-Salam, SemEval 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.semeval-1.126.pdf
- Code
- rematchka/intended-sarcasm-detection-in-english-and-arabic-for-extremly-unbalanced-datasets