Browsing by Author "Suzgun, Mirac"

Now showing items 1-2 of 2

    • LSTM Networks Can Perform Dynamic Counting 

      Suzgun, Mirac; Gehrmann, Sebastian; Belinkov, Yonatan; Shieber, Stuart (2019-06-09)
      In this paper, we systematically assess the ability of standard recurrent networks to perform dynamic counting and to encode hierarchical representations. All the neural models in our experiments are designed to be small-sized ...

    • On Evaluating the Generalization of LSTM Models in Formal Languages 

      Suzgun, Mirac; Belinkov, Yonatan; Shieber, Stuart (Society for Computation in Linguistics, 2019-01)
      Recurrent Neural Networks (RNNs) are theoretically Turing-complete and established themselves as a dominant model for language processing. Yet, there still remains an uncertainty regarding their language learning capabilities. ...