发现罕见不规则形态导致模型错误集中，且其影响远超其他不规则形式。
When Irregularity Helps: A Subclass Analysis of Inductive Bias in Neural Morphology
- 聚焦日语动词过去式中占比不足1%的特殊不规则子类
- 移除该子类使泛化性能提升，优于移除全部不规则词
- 提示评估应细化到更具体的形态子类，而非仅按常规变位分类
神经形态生成系统在基准数据集上常表现出高总体准确率，但这种表现可能掩盖了在罕见形态子类上的系统性错误。我们以日语过去时动词变位为例，发现一个结构特定、占比小于1%的不规则子类，占了模型错误的极大比例。控制性消融实验表明，移除该子类带来的泛化性能提升，大于移除所有不规则词的效果，说明并非所有不规则性对模型稳定性的影响相同。研究指出，错误集中源于极端低频形态模式与特定音变过程（尤其是辅音延长）之间的相互作用。因此，我们主张形态评估应超越标准变位类别，引入更细粒度的子类分析。
原文摘要 · Abstract (English)
Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors concentrated in rare morphological subclasses. We examine Japanese past-tense verb inflection and show that a very small, structurally specific irregular subtype (<1% of data) accounts for a disproportionate share of model errors. Controlled ablation experiments demonstrate that removing this subtype yields larger improvements in generalization than removing all irregular verbs, indicating that not all irregularity contributes equally to model instability. These findings suggest that error concentration is driven by the interaction between extreme low-frequency morphological patterns and specific morphophonological processes, particularly gemination. We argue that morphological evaluation should incorporate finer-grained subclass analysis beyond standard conjugation categories.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。