Were We There Already? Applying Minimal Generalization to the SIGMORPHON-UniMorph Shared Task on Cognitively Plausible Morphological Inflection

Abstract

Morphological rules with various levels of specificity can be learned from example lexemes by recursive application of minimal generalization (Albright and Hayes, 2002, 2003). A model that learns rules solely through minimal generalization was used to predict average human wug-test ratings from German, English, and Dutch in the SIGMORPHONUniMorph 2021 Shared Task, with competitive results. Some formal properties of the minimal generalization operation were proved,experimentalntially pruned. An automatic method was developed to create wugtest stimuli for future experiments that investigate whether the model’s morphological generalizations are too minimal.