@article{schneider-etal-2014-discriminative,
    title = "Discriminative Lexical Semantic Segmentation with Gaps: Running the {MWE} Gamut",
    author = "Schneider, Nathan  and
      Danchik, Emily  and
      Dyer, Chris  and
      Smith, Noah A.",
    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/jlcl-multiple-ingestion/Q14-1016/",
    doi = "10.1162/tacl_a_00176",
    pages = "193--206",
    abstract = "We present a novel representation, evaluation measure, and supervised models for the task of identifying the multiword expressions (MWEs) in a sentence, resulting in a lexical semantic segmentation. Our approach generalizes a standard chunking representation to encode MWEs containing gaps, thereby enabling efficient sequence tagging algorithms for feature-rich discriminative models. Experiments on a new dataset of English web text offer the first linguistically-driven evaluation of MWE identification with truly heterogeneous expression types. Our statistical sequence model greatly outperforms a lookup-based segmentation procedure, achieving nearly 60{\%} F1 for MWE identification."
}