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

arXiv: https://arxiv.org/abs/2609.21179 · HTML: https://mlsanity.com/paper/2609.21179/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Information-Theoretic Probing for Linguistic Structure](https://mlsanity.com/paper/2004.03061/) (2020)
- [Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging](https://mlsanity.com/paper/1707.09861/) (2017)
- [The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection](https://mlsanity.com/paper/1810.07125/) (2018)
- [CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages](https://mlsanity.com/paper/1706.09031/) (2017)
- [SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection](https://mlsanity.com/paper/2006.11572/) (2020)
- [Morphological Irregularity Correlates with Frequency](https://mlsanity.com/paper/1906.11483/) (2019)
- [Single-Model Encoder-Decoder with Explicit Morphological Representation for Reinflection](https://mlsanity.com/paper/1606.00589/) (2016)
- [Imitation Learning for Neural Morphological String Transduction](https://mlsanity.com/paper/1808.10701/) (2018)
- [Frequency matters: Modeling irregular morphological patterns in Spanish with Transformers](https://mlsanity.com/paper/2410.21013/) (2024)
- [Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation](https://mlsanity.com/paper/2608.25089/) (2026)
- [Mind Your Moras: Orthography-Aware Error Analysis of Neural Japanese Morphological Generation](https://mlsanity.com/paper/2605.20043/) (2026)
- [When Irregularity Helps: A Subclass Analysis of Inductive Bias in Neural Morphology](https://mlsanity.com/paper/2605.20558/) (2026)

## Abstract (arXiv)

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 irregular subtype, verbs whose stems end in /e/ and require gemination before the past-tense suffix and make up fewer than 1% of the data, accounts for a disproportionate 30-43% share of residual errors and contributes roughly 34-48x its prevalence to total errors. We then move from diagnosis to causal isolation: controlled ablation experiments show that removing this subtype alone produces larger accuracy gains than removing all irregular verbs combined. These findings indicate that error concentration in neural morphological learning is not driven by irregularity per se, but by the interaction between extreme low-frequency morphological patterns and specific orthographic processes. We argue that morphological evaluation should incorporate fine-grained subclass analysis, and discuss implications for data-efficient, developmentally plausible language model pretraining.