@article{cotterell-etal-2019-complexity,
    title = "On the Complexity and Typology of Inflectional Morphological Systems",
    author = "Cotterell, Ryan  and
      Kirov, Christo  and
      Hulden, Mans  and
      Eisner, Jason",
    editor = "Lee, Lillian  and
      Johnson, Mark  and
      Roark, Brian  and
      Nenkova, Ani",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "7",
    year = "2019",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/Q19-1021/",
    doi = "10.1162/tacl_a_00271",
    pages = "327--342",
    abstract = "We quantify the linguistic complexity of different languages' morphological systems. We verify that there is a statistically significant empirical trade-off between paradigm size and irregularity: A language`s inflectional paradigms may be either large in size or highly irregular, but never both. We define a new measure of paradigm irregularity based on the conditional entropy of the surface realization of a paradigm{---} how hard it is to jointly predict all the word forms in a paradigm from the lemma. We estimate irregularity by training a predictive model. Our measurements are taken on large morphological paradigms from 36 typologically diverse languages."
}