An Information-Theoretic Foundation for the Subregular Hierarchy
Mai Phan Quoc Hung, Khanh Nguyen Quoc, Doàn Minh Luong, Duong Thu Ngan, Duong Thi Phuong Thao, Tuan Do
Abstract
The Subregular Hypothesis posits that phonological patterns in natural languages occupy a restricted region of the formal language hierarchy, yet the cognitive basis for this restriction remains unclear. We propose an informationtheoretic characterization: Strictly Local languages, when formalized as shifts of finite type, are exactly those admitting stationary Markov sources, which exhibit zero conditional mutual information between distant positions given intervening symbols. We prove that certain nonsubregular patterns such as first-last assimilation admit no such Markov realization, explaining their unlearnability. Empirical validation on English phonotactics versus Finnish, Turkish, and Hungarian vowel harmony confirms that MI profiles statistically distinguish SL-like from TSL-like patterns (p < 0.001, r = 0.84). This work bridges formal language theory and information theory, offering a unified framework for understanding computational restrictions on natural language phonology.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 4d727ad2-bc41-48e2-8e89-b8d4a67bd86aBuilds on1
Related papers
- Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-AccentEthan Wilcox, Cui Ding, Giovanni Acampa, Tiago Pimentel et al.ACL 2025 · 3 citations
- Vocabulary Shapes Cross-Lingual Variation of Word-Order Learnability in Language ModelsJonas Mayer Martins, Jaap Jumelet, Viola Priesemann, Lisa BeinbornACL 2026
- Information Locality as an Inductive Bias for Neural Language ModelsTaiga Someya, Anej Svete, Brian DuSell, Timothy J. O'Donnell et al.ACL 2025 · 6 citations
- Arrows of Time for Large Language ModelsVassilis Papadopoulos, Jérémie Wenger, Clément HonglerICML 2024 · 16 citations
- Language Generation in the Limit: Complexity Barriers and Implications for LearningMarcelo Arenas, Pablo Barcelo, Luis Cofré, Alexander KozachinskiyICML 2026
