@article{brooke-etal-2017-unsupervised,
    title = "Unsupervised Acquisition of Comprehensive Multiword Lexicons using Competition in an n-gram Lattice",
    author = "Brooke, Julian  and
      {\v{S}}najder, Jan  and
      Baldwin, Timothy",
    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/jlcl-multiple-ingestion/Q17-1032/",
    doi = "10.1162/tacl_a_00073",
    pages = "455--470",
    abstract = "We present a new model for acquiring comprehensive multiword lexicons from large corpora based on competition among n-gram candidates. In contrast to the standard approach of simple ranking by association measure, in our model n-grams are arranged in a lattice structure based on subsumption and overlap relationships, with nodes inhibiting other nodes in their vicinity when they are selected as a lexical item. We show how the configuration of such a lattice can be optimized tractably, and demonstrate using annotations of sampled n-grams that our method consistently outperforms alternatives by at least 0.05 F-score across several corpora and languages."
}