paper-with-me

Papers

Evaluating the relationship between regularity and learnability in recursive numeral systems using Reinforcement Learning

2026-02-25 · Andrea Silvi, Ponrawee Prasertsom, Jennifer Culbertson, Devdatt Dubhashi, Moa Johansson, Kenny Smith arxiv

Human recursive numeral systems (i.e., counting systems such as English base-10 numerals), like many other grammatical systems, are highly regular. Following prior work that relates cross-linguistic tendencies to biases in learning, we ask whether regular systems are common because regularity facilitates learning. Adopting methods from the Reinforcement Learning literature, we confirm that highly regular human(-like) systems are easier to learn than unattested but possible irregular systems. This asymmetry emerges under the natural assumption that recursive numeral systems are designed for generalisation from limited data to represent all integers exactly. We also find that the influence of regularity on learnability is absent for unnatural, highly irregular systems, whose learnability is influenced instead by signal length, suggesting that different pressures may influence learnability differently in different parts of the space of possible numeral systems. Our results contribute to the body of work linking learnability to cross-linguistic prevalence.

📄 PDF Abstract BibTeX arXiv:2602.21720

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Causally Evaluating the Learnability of Formal Language Tasks

2026-06-08 · Vésteinn Snæbjarnarson, Anej Svete, Josef Valvoda, Reda Boumasmoud 외 arxiv

Language models, as multi-task learners, acquire a wide range of abilities during training. A fundamental question is how much task-specific data is needed to learn a given task. Answering this for natural language is di…

Recursive numeral systems are highly regular and easy to process

2025-10-30 · Ponrawee Prasertsom, Andrea Silvi, Jennifer Culbertson, Moa Johansson 외 arxiv

Much recent work has shown how cross-linguistic variation is constrained by competing pressures from efficient communication. However, little attention has been paid to the role of the systematicity of forms (regularity)…

Vocabulary shapes cross-lingual variation of word-order learnability in language models

2026-03-19 · Jonas Mayer Martins, Jaap Jumelet, Viola Priesemann, Lisa Beinborn arxiv

Why do some languages like Czech permit free word order, while others like English do not? We address this question by pretraining transformer language models on a spectrum of synthetic word-order variants of natural lan…

Distribution Learnability and Robustness

2024-06-25 · NeurIPS 2023 11 · Shai Ben-David, Alex Bie, Gautam Kamath, Tosca Lechner

We examine the relationship between learnability and robust (or agnostic) learnability for the problem of distribution learning. We show that, contrary to other learning settings (e.g., PAC learning of function classes),…

PAC learning

Recursively Enumerably Representable Classes and Computable Versions of the Fundamental Theorem of Statistical Learning

2025-11-04 · David Kattermann, Lothar Sebastian Krapp arxiv

We study computable probably approximately correct (CPAC) learning, where learners are required to be computable functions. It had been previously observed that the Fundamental Theorem of Statistical Learning, which char…