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

  title={UM-IU@LING at SemEval-2019 Task 6: Identifying Offensive Tweets Using BERT and SVMs},
  author={Jian Zhu and Zuoyu Tian and Sandra K{\"u}bler},
  • Jian Zhu, Zuoyu Tian, Sandra Kübler
  • Published in SemEval@NAACL-HLT 2019
  • Computer Science
  • 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… CONTINUE READING
    19 Citations

    Figures, Tables, and Topics from this paper

    CoLi at UdS at SemEval-2020 Task 12: Offensive Tweet Detection with Ensembling
    • 1
    • Highly Influenced
    • PDF
    Amsqr at SemEval-2020 Task 12: Offensive Language Detection Using Neural Networks and Anti-adversarial Features
    • 1
    • PDF
    Offensive Language Detection Using Brown Clustering
    • PDF
    Neural Word Decomposition Models for Abusive Language Detection
    • 11
    • PDF
    Aggression Identification in Social Media: a Transfer Learning Based Approach
    • PDF


    SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)
    • 270
    • PDF
    Challenges in discriminating profanity from hate speech
    • 128
    • Highly Influential
    • PDF
    Deep Learning for Hate Speech Detection in Tweets
    • 411
    • PDF
    Benchmarking Aggression Identification in Social Media
    • 192
    • PDF
    Hate Speech Detection with Comment Embeddings
    • 333
    • PDF
    Locate the Hate: Detecting Tweets against Blacks
    • 216
    • PDF
    Modeling the Detection of Textual Cyberbullying
    • 345
    • PDF