A structurally specific irregular verb subclass under 1% of Japanese past-tense data drives disproportionate errors in neural morphology models, with ablation showing its removal aids generalization more than removing all irregulars.
Retaining other irregular subtypes (4-1 and 4-3) produces lower error rates than a purely regular training regime
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When Irregularity Helps: A Subclass Analysis of Inductive Bias in Neural Morphology
A structurally specific irregular verb subclass under 1% of Japanese past-tense data drives disproportionate errors in neural morphology models, with ablation showing its removal aids generalization more than removing all irregulars.