Open AccessLinguisticsComputer Science

Micha Elsner, Andrea D. Sims, Alexander Erdmann, A. Hernandez, Evan Jaffe, Lifeng Jin, Martha Booker Johnson, Shuan O. Karim, David L. King, Luana Lamberti Nunes, Byung-Doh Oh, Nathan Rasmussen, Cory Shain, Stephanie Antetomaso, Kendra V. Dickinson, N. Diewald, Michelle Mckenzie, S. Stevens-Guille

2019.12.19Journal of Language Modelling

DOI: 10.15398/jlm.v7i1.244

tlooto Summary

Research using neural sequence-to-sequence models as compu-tational models of morphological learning and learnability is surveyed and some proposals for future work in these areas are made.

Abstract

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.

Citation format

ELSNER, Micha, et al. Modeling morphological learning, typology, and change: What can the neural sequence-to-sequence framework contribute? Journal of Language Modelling, 2019.