Modeling morphological learning, typology, and change: What can the neural sequence-to-sequence framework contribute?
Micha Elsner, Andrea D. Sims, Alexander Erdmann, Antonio Ordaz Hernández, Evan Jaffe, Lifeng Jin, Martha Booker Johnson, Shuan Osman Karim, David King, Luana Lamberti, Byung-Doh Oh, Nathan Rasmussen, Cory Shain, Stephanie Antetomaso, Kendra V. Dickinson, Noah Diewald, Michelle McKenzie, Symon Jory Stevens-Guille · Journal of Language Modelling · 2019
We survey research using neural sequence-to-sequence models as compu-tational models of morphological learning and learnability. We discusstheir use in determining the predictability of inflectional exponents, inmaking predictions about language acquisition and in modeling languagechange. Finally, we make some proposals for future work in these areas.