Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge
This work addresses the problem of understanding cross-linguistic transfer in morphology acquisition for computational linguistics and language modeling, but it is incremental as it builds on existing sequence-to-sequence methods.
The study investigated how prior knowledge of one language's morphology influences learning of inflection rules in a second language using a sequence-to-sequence neural network trained on combinations of eight source and three target languages, finding that closely related languages ease acquisition, differing affixation patterns increase difficulty, and agglutinative source languages simplify learning regardless of relatedness.
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.