Abstract | ||
---|---|---|
This paper describes the UM-IU@LINGu0027s system for the SemEval 2019 Task 6: OffensEval. We take a mixed approach to identify and categorize hate speech in social media. In subtask A, we fine-tuned a BERT based classifier to detect abusive content in tweets, achieving a macro F1 score of 0.8136 on the test data, thus reaching the 3rd rank out of 103 submissions. In subtasks B and C, we used a linear SVM with selected character n-gram features. For subtask C, our system could identify the target of abuse with a macro F1 score of 0.5243, ranking it 27th out of 65 submissions. |
Year | Venue | Field |
---|---|---|
2019 | North American Chapter of the Association for Computational Linguistics | Categorization,F1 score,SemEval,Ranking,Computer science,Support vector machine,Natural language processing,Artificial intelligence,Test data,Classifier (linguistics),Macro,Machine learning |
DocType | Volume | Citations |
Journal | abs/1904.03450 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jian Zhu | 1 | 15 | 4.11 |
Zuoyu Tian | 2 | 0 | 1.01 |
Sandra Kübler | 3 | 56 | 13.29 |