@article{lewis-steedman-2014-improved,
    title = "Improved {CCG} Parsing with Semi-supervised Supertagging",
    author = "Lewis, Mike  and
      Steedman, Mark",
    editor = "Lin, Dekang  and
      Collins, Michael  and
      Lee, Lillian",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "2",
    year = "2014",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/ingest-emnlp/Q14-1026/",
    doi = "10.1162/tacl_a_00186",
    pages = "327--338",
    abstract = "Current supervised parsers are limited by the size of their labelled training data, making improving them with unlabelled data an important goal. We show how a state-of-the-art CCG parser can be enhanced, by predicting lexical categories using unsupervised vector-space embeddings of words. The use of word embeddings enables our model to better generalize from the labelled data, and allows us to accurately assign lexical categories without depending on a POS-tagger. Our approach leads to substantial improvements in dependency parsing results over the standard supervised CCG parser when evaluated on Wall Street Journal (0.8{\%}), Wikipedia (1.8{\%}) and biomedical (3.4{\%}) text. We compare the performance of two recently proposed approaches for classification using a wide variety of word embeddings. We also give a detailed error analysis demonstrating where using embeddings outperforms traditional feature sets, and showing how including POS features can decrease accuracy."
}