Abstract
We examine learning offensive content on Twitter with limited, imbalanced data. For the purpose, we investigate the utility of using various data enhancement methods with a host of classical ensemble classifiers. Among the 75 participating teams in SemEval-2019 sub-task B, our system ranks 6th (with 0.706 macro F1-score). For sub-task C, among the 65 participating teams, our system ranks 9th (with 0.587 macro F1-score).- Anthology ID:
- S19-2136
- Volume:
- Proceedings of the 13th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota, USA
- Editors:
- Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 775–781
- Language:
- URL:
- https://aclanthology.org/S19-2136
- DOI:
- 10.18653/v1/S19-2136
- Cite (ACL):
- Arun Rajendran, Chiyu Zhang, and Muhammad Abdul-Mageed. 2019. UBC-NLP at SemEval-2019 Task 6: Ensemble Learning of Offensive Content With Enhanced Training Data. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 775–781, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
- Cite (Informal):
- UBC-NLP at SemEval-2019 Task 6: Ensemble Learning of Offensive Content With Enhanced Training Data (Rajendran et al., SemEval 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/S19-2136.pdf