Modeling morphological learning, typology, and change: What can the neural sequence-to-sequence framework contribute?


Micha Elsner, The Ohio State University, United States
Andrea D. Sims, The Ohio State University,
Alexander Erdmann, The Ohio State University,
Antonio Hernandez, The Ohio State University,
Evan Jaffe, The Ohio State University,
Lifeng Jin, The Ohio State University,
Martha Booker Johnson, The Ohio State University,
Shuan Karim, The Ohio State University,
David L. King, The Ohio State University,
Luana Lamberti Nunes, The Ohio State University,
Byung-Doh Oh, The Ohio State University,
Nathan Rasmussen, The Ohio State University,
Cory Shain, The Ohio State University,
Stephanie Antetomaso, The Ohio State University,
Kendra V. Dickinson, The Ohio State University,
Noah Diewald, The Ohio State University,
Michelle McKenzie, The Ohio State University,
Symon Stevens-Guille, The Ohio State University,

Abstract


We survey research using neural sequence-to-sequence models as compu-
tational models of morphological learning and learnability. We discuss
their use in determining the predictability of inflectional exponents, in
making predictions about language acquisition and in modeling language
change. Finally, we make some proposals for future work in these areas.


Keywords


morphology; computational modeling; typology

Full Text:

PDF


DOI: http://dx.doi.org/10.15398/jlm.v7i1.244

ISSN of the paper edition: 2299-856X