Papers › UM-IU@LING at SemEval-2019 Task 6: Identifying Offensive Tweets Using BERT and SVMs

UM-IU@LING at SemEval-2019 Task 6: Identifying Offensive Tweets Using BERT and SVMs

6 Apr 2019SEMEVAL 2019 6arXiv:1904.03450archive 2025-07-28

Jian Zhu, Zuoyu Tian, Sandra Kübler

This paper describes the UM-IU@LING's 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.

PaperPDFConference PDFCode

Code

zytian9/SemEval-2019-Task-6 officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Abuse Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSVMSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections