@inproceedings{seeberger-riedhammer-2022-enhancing,
    title = "Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning",
    author = "Seeberger, Philipp  and
      Riedhammer, Korbinian",
    editor = "Biester, Laura  and
      Demszky, Dorottya  and
      Jin, Zhijing  and
      Sachan, Mrinmaya  and
      Tetreault, Joel  and
      Wilson, Steven  and
      Xiao, Lu  and
      Zhao, Jieyu",
    booktitle = "Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.nlp4pi-1.9/",
    doi = "10.18653/v1/2022.nlp4pi-1.9",
    pages = "70--78",
    abstract = "Social media has become an important information source for crisis management and provides quick access to ongoing developments and critical information. However, classification models suffer from event-related biases and highly imbalanced label distributions which still poses a challenging task. To address these challenges, we propose a combination of entity-masked language modeling and hierarchical multi-label classification as a multi-task learning problem. We evaluate our method on tweets from the TREC-IS dataset and show an absolute performance gain w.r.t. F1-score of up to 10{\%} for actionable information types. Moreover, we found that entity-masking reduces the effect of overfitting to in-domain events and enables improvements in cross-event generalization."
}