Seq2Seq Models with Dropout can Learn Generalizable Reduplication
Brandon Prickett, Aaron Traylor, Joe Pater · 2018
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.(2001), Smolensky andLegendre (2006), andMoreton (2012).See Pater (2018: §4) for a more detailed discussion of different hybrids of connectionist and symbolic approaches.