KAFK at SemEval-2020 Task 12: Checkpoint Ensemble of Transformers for Hate Speech Classification
Kaushik Amar Das, Arup Baruah, Ferdous Ahmed Barbhuiya, Kuntal Dey
Abstract
This paper presents the approach of Team KAFK for the English edition of SemEval-2020 Task 12. We use checkpoint ensembling to create ensembles of BERT-based transformers and show that it can improve the performance of classification systems. We explore attention mask dropout to mitigate for the poor constructs of social media texts. Our classifiers scored macro-f1 of 0.909, 0.551 and 0.616 for subtasks A, B and C respectively. The code is publicly released online.- Anthology ID:
- 2020.semeval-1.267
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 2023–2029
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.267
- DOI:
- 10.18653/v1/2020.semeval-1.267
- Cite (ACL):
- Kaushik Amar Das, Arup Baruah, Ferdous Ahmed Barbhuiya, and Kuntal Dey. 2020. KAFK at SemEval-2020 Task 12: Checkpoint Ensemble of Transformers for Hate Speech Classification. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 2023–2029, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- KAFK at SemEval-2020 Task 12: Checkpoint Ensemble of Transformers for Hate Speech Classification (Das et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2020.semeval-1.267.pdf
- Code
- cozek/OffensEval2020-code