@InProceedings{prickett-traylor-pater:2018:SIGMORPHON,
  author    = {Prickett, Brandon  and  Traylor, Aaron  and  Pater, Joe},
  title     = {Seq2Seq Models with Dropout can Learn Generalizable Reduplication},
  booktitle = {Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology},
  month     = {October},
  year      = {2018},
  address   = {Brussels, Belgium},
  publisher = {Association for Computational Linguistics},
  pages     = {93--100},
  abstract  = {Natural language reduplication can pose a challenge to neural models of language, and has been argued to require variables (Marcus et al., 1999). Sequence-to-sequence neural networks have been shown to perform well at a number of other morphological tasks (Cotterell et al., 2016), and produce results that highly correlate with human behavior (Kirov, 2017; Kirov \& Cotterell, 2018) but do not include any explicit variables in their architecture. We find that they can learn a reduplicative pattern that generalizes to novel segments if they are trained with dropout (Srivastava et al., 2014). We argue that this matches the scope of generalization observed in human reduplication.},
  url       = {http://www.aclweb.org/anthology/W18-5810}
}