From Formal Language Theory to Statistical Learning: Finite Observability of Subregular Languages
This provides a rigorous and interpretable foundation for modeling natural language structure, bridging formal language theory and statistical learning.
The paper proved that all standard subregular language classes are linearly separable when represented by their deciding predicates, establishing finite observability and learnability with simple linear models. Synthetic experiments confirmed perfect separability under noise-free conditions, while real-data experiments on English morphology showed learned features align with known linguistic constraints.
We prove that all standard subregular language classes are linearly separable when represented by their deciding predicates. This establishes finite observability and guarantees learnability with simple linear models. Synthetic experiments confirm perfect separability under noise-free conditions, while real-data experiments on English morphology show that learned features align with well-known linguistic constraints. These results demonstrate that the subregular hierarchy provides a rigorous and interpretable foundation for modeling natural language structure. Our code used in real-data experiments is available at https://github.com/UTokyo-HayashiLab/subregular.