@inproceedings{sikdar-gamback-2017-feature,
    title = "A Feature-based Ensemble Approach to Recognition of Emerging and Rare Named Entities",
    author = {Sikdar, Utpal Kumar  and
      Gamb{\"a}ck, Bj{\"o}rn},
    editor = "Derczynski, Leon  and
      Xu, Wei  and
      Ritter, Alan  and
      Baldwin, Tim",
    booktitle = "Proceedings of the 3rd Workshop on Noisy User-generated Text",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W17-4424/",
    doi = "10.18653/v1/W17-4424",
    pages = "177--181",
    abstract = "Detecting previously unseen named entities in text is a challenging task. The paper describes how three initial classifier models were built using Conditional Random Fields (CRFs), Support Vector Machines (SVMs) and a Long Short-Term Memory (LSTM) recurrent neural network. The outputs of these three classifiers were then used as features to train another CRF classifier working as an ensemble. 5-fold cross-validation based on training and development data for the emerging and rare named entity recognition shared task showed precision, recall and F1-score of 66.87{\%}, 46.75{\%} and 54.97{\%}, respectively. For surface form evaluation, the CRF ensemble-based system achieved precision, recall and F1 scores of 65.18{\%}, 45.20{\%} and 53.30{\%}. When applied to unseen test data, the model reached 47.92{\%} precision, 31.97{\%} recall and 38.55{\%} F1-score for entity level evaluation, with the corresponding surface form evaluation values of 44.91{\%}, 30.47{\%} and 36.31{\%}."
}