← smac.pub home

GUIR at SemEval-2020 Task 12: Domain-Tuned Contextualized Models for Offensive Language Detection

pdf arxiv bibtex workshop paper system description paper to appear

Authors: Sajad Sotudeh*, Tong Xiang*, Hao-Ren Yao, Sean MacAvaney, Eugene Yang, Nazli Goharian, Ophir Frieder

* equal contribution

Appearing in: Proceedings of the 14th International Workshop on Semantic Evaluation (SemEval @ COLING 2020)

Abstract:

Offensive language detection is an important and challenging task in natural language pro cessing. We present our submissions to the OffensEval 2020 shared task, which includes three English sub-tasks: identifying the presence of offensive language (Sub-task A), identifying the presence of target in offensive language (Sub-task B), and identifying the categories of the target (Sub-task C). Our experiments explore using a domain-tuned contextualized language model (namely, BERT) for this task. We also experiment with different components and configurations (e.g., a multi-view SVM) stacked upon BERT models for specific sub-tasks. Our submissions achieve F1 scores of 91.7% in Sub-task A, 66.5% in Sub-task B, and 63.2% in Sub-task C. We perform an ablation study which reveals that domain tuning considerably improves the classification performance. Furthermore, error analysis shows common misclassification errors made by our model and outlines research directions for future.

BibTeX @inproceedings{sotudeh:semeval2020-offenseval, author = {Sotudeh, Sajad and Xiang, Tong and Yao, Hao-Ren and MacAvaney, Sean and Yang, Eugene and Goharian, Nazli and Frieder, Ophir}, title = {GUIR at SemEval-2020 Task 12: Domain-Tuned Contextualized Models for Offensive Language Detection}, booktitle = {Proceedings of the 14th International Workshop on Semantic Evaluation}, year = {2020}, url = {https://arxiv.org/abs/2007.14477} }