@inproceedings{piskorski-etal-2020-new,
    title = "New Benchmark Corpus and Models for Fine-grained Event Classification: To {BERT} or not to {BERT}?",
    author = "Piskorski, Jakub  and
      Haneczok, Jacek  and
      Jacquet, Guillaume",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2020.coling-main.584/",
    doi = "10.18653/v1/2020.coling-main.584",
    pages = "6663--6678",
    abstract = "We introduce a new set of benchmark datasets derived from ACLED data for fine-grained event classification and compare the performance of various state-of-the-art models on these datasets, including SVM based on TF-IDF character n-grams and neural context-free embeddings (GLOVE and FASTTEXT) as well as deep learning-based BERT with its contextual embeddings. The best results in terms of micro (94.3-94.9{\%}) and macro F1 (86.0-88.9{\%}) were obtained using BERT transformer, with simpler TF-IDF character n-gram based SVM being an interesting alternative. Further, we discuss the pros and cons of the considered benchmark models in terms of their robustness and the dependence of the classification performance on the size of training data."
}