SOURCE-LINKED INTELLIGENCE

Not All Irregularity Is Equal: Causally Isolating a Rare Failure Mode in Japanese Morphological Inflection

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors clustered in rare morphological subclasses. We present an orthography-aware diagnosis of Japanese past-tense verb inflection, treating hiragana not merely as a transcriptional medium but as a representational system that encodes morphophonological structure. Using two character-level Transformer architectures evaluated across five random seeds, we show that although both systems exceed 97% aggregate accuracy, a single structurally specific irre

Read original source ↗ Open in workspace

recordType

paper

region

Global