@inproceedings{verma-etal-2022-claclab,
    title = "{CL}a{CL}ab at {S}ocial{D}is{NER}: Using Medical Gazetteers for Named-Entity Recognition of Disease Mentions in {S}panish Tweets",
    author = "Verma, Harsh  and
      Bagherzadeh, Parsa  and
      Bergler, Sabine",
    editor = "Gonzalez-Hernandez, Graciela  and
      Weissenbacher, Davy",
    booktitle = "Proceedings of the Seventh Workshop on Social Media Mining for Health Applications, Workshop {\&} Shared Task",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.smm4h-1.16/",
    pages = "55--57",
    abstract = "This paper summarizes the CLaC submission for SMM4H 2022 Task 10 which concerns the recognition of diseases mentioned in Spanish tweets. Before classifying each token, we encode each token with a transformer encoder using features from Multilingual RoBERTa Large, UMLS gazetteer, and DISTEMIST gazetteer, among others. We obtain a strict F1 score of 0.869, with competition mean of 0.675, standard deviation of 0.245, and median of 0.761."
}