@inproceedings{doucette-2017-inherent,
    title = "Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation",
    author = "Doucette, Amanda",
    editor = "Gibson, Ted  and
      Linzen, Tal  and
      Sayeed, Asad  and
      van Schijndel, Marten  and
      Schuler, William",
    booktitle = "Proceedings of the 7th Workshop on Cognitive Modeling and Computational Linguistics ({CMCL} 2017)",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W17-0705/",
    doi = "10.18653/v1/W17-0705",
    pages = "35--40",
    abstract = "A recurrent neural network model of phonological pattern learning is proposed. The model is a relatively simple neural network with one recurrent layer, and displays biases in learning that mimic observed biases in human learning. Single-feature patterns are learned faster than two-feature patterns, and vowel or consonant-only patterns are learned faster than patterns involving vowels and consonants, mimicking the results of laboratory learning experiments. In non-recurrent models, capturing these biases requires the use of alpha features or some other representation of repeated features, but with a recurrent neural network, these elaborations are not necessary."
}