Paper

Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge

---

Abstract

How does knowledge of one language’s morphology influence learning of inflection rules in a second one? In order to investigate this question in artificial neural network models, we perform experiments with a sequence-to-sequence architecture, which we train on different combinations of eight source and three target languages. A detailed analysis of the model outputs suggests the following conclusions: (i) if source and target language are closely related, acquisition of the target language’s inflectional morphology constitutes an easier task for the model; (ii) knowledge of a prefixing (resp. suffixing) language makes acquisition of a suffixing (resp. prefixing) language’s morphology more challenging; and (iii) surprisingly, a source language which exhibits an agglutinative morphology simplifies learning of a second language’s inflectional morphology, independent of their relatedness.

Keywords: Morphology, Neural Network, Deep Learning, Inflection, Transfer Learning, Pretraining

How to Cite:

Kann, K., (2020) “Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge”, Society for Computation in Linguistics 3(1), 99-109. doi: https://doi.org/10.7275/zwwg-0g10