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

Szczegóły
Abstrakt

Tytuł:: Modeling morphological learning, typology, and change : What can the neural sequence-to-sequence framework contribute?
Autorzy:: Elsner, Micha
Sims, Andrea D.
Erdmann, Alexander
Hernandez, Antonio
Jaffe, Evan
Jin, Lifeng
Booker Johnson, Martha
Karim, Shuan
King, David L.
Lamberti Nunes, Luana
Oh, Byung-Doh
Rasmussen, Nathan
Shain, Cory
Antetomaso, Stephanie
Dickinson, Kendra V.
Diewald, Noah
McKenzie, Michelle
Stevens-Guille, Symon
Data publikacji:: 2019
Słowa kluczowe:: morphology
computational modeling
typology
Język:: angielski
Dostawca treści:: BazTech
: Artykuł

We survey research using neural sequence-to-sequence models as computational 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.

Informacja

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