@article{berend-2017-sparse,
    title = "Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling",
    author = "Berend, G{\'a}bor",
    editor = "Lee, Lillian  and
      Johnson, Mark  and
      Toutanova, Kristina",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "5",
    year = "2017",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/ingest-emnlp/Q17-1018/",
    doi = "10.1162/tacl_a_00059",
    pages = "247--261",
    abstract = "In this paper we propose and carefully evaluate a sequence labeling framework which solely utilizes sparse indicator features derived from dense distributed word representations. The proposed model obtains (near) state-of-the art performance for both part-of-speech tagging and named entity recognition for a variety of languages. Our model relies only on a few thousand sparse coding-derived features, without applying any modification of the word representations employed for the different tasks. The proposed model has favorable generalization properties as it retains over 89.8{\%} of its average POS tagging accuracy when trained at 1.2{\%} of the total available training data, i.e. 150 sentences per language."
}