@InProceedings{aglionby-EtAl:2019:S19-2,
  author    = {Aglionby, Guy  and  Davis, Chris  and  Mishra, Pushkar  and  Caines, Andrew  and  Yannakoudakis, Helen  and  Rei, Marek  and  Shutova, Ekaterina  and  Buttery, Paula},
  title     = {CAMsterdam at SemEval-2019 Task 6: Neural and graph-based feature extraction for the identification of offensive tweets},
  booktitle = {Proceedings of the 13th International Workshop on Semantic Evaluation},
  month     = {June},
  year      = {2019},
  address   = {Minneapolis, Minnesota, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {556--563},
  abstract  = {We describe the CAMsterdam team entry to the SemEval-2019 Shared Task 6 on offensive language identification in Twitter data. Our proposed model learns to extract textual features using a multi-layer recurrent network, and then performs text classification using gradient-boosted decision trees (GBDT). A self-attention architecture enables the model to focus on the most relevant areas in the text. In order to enrich input representations, we use node2vec to learn globally optimised embeddings for hashtags, which are then given as additional features to the GBDT classifier. Our best model obtains 78.79\% macro F1-score on detecting offensive language (subtask A), 66.32\% on categorising offence types (targeted/untargeted; subtask B), and 55.36\% on identifying the target of offence (subtask C).},
  url       = {http://www.aclweb.org/anthology/S19-2100}
}