@inproceedings{damaschk-etal-2019-multiclass,
    title = "Multiclass Text Classification on Unbalanced, Sparse and Noisy Data",
    author = {D{\"o}nicke, Tillmann  and
      Damaschk, Matthias  and
      Lux, Florian},
    editor = {Nivre, Joakim  and
      Derczynski, Leon  and
      Ginter, Filip  and
      Lindi, Bj{\o}rn  and
      Oepen, Stephan  and
      S{\o}gaard, Anders  and
      Tidemann, J{\"o}rg},
    booktitle = "Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing",
    month = sep,
    year = "2019",
    address = "Turku, Finland",
    publisher = {Link{\"o}ping University Electronic Press},
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W19-6207/",
    pages = "58--65",
    abstract = "This paper discusses methods to improve the performance of text classification on data that is difficult to classify due to a large number of unbalanced classes with noisy examples. A variety of features are tested, in combination with three different neural-network-based methods with increasing complexity. The classifiers are applied to a songtext{--}artist dataset which is large, unbalanced and noisy. We come to the conclusion that substantial improvement can be obtained by removing unbalancedness and sparsity from the data. This fulfils a classification task unsatisfactorily{---}however, with contemporary methods, it is a practical step towards fairly satisfactory results."
}