# One Model for the Learning of Language

arXiv: https://arxiv.org/abs/1711.06301 · HTML: https://mlsanity.com/paper/1711.06301/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2017.

## Built on by (most cited first, 22 of 22)

- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [Modeling rapid language learning by distilling Bayesian priors into artificial neural networks](https://mlsanity.com/paper/2305.14701/) (2023)
- [The Relational Bottleneck as an Inductive Bias for Efficient Abstraction](https://mlsanity.com/paper/2309.06629/) (2023)
- [Minimum Description Length Recurrent Neural Networks](https://mlsanity.com/paper/2111.00600/) (2021)
- [Bayes in the age of intelligent machines](https://mlsanity.com/paper/2311.10206/) (2023)
- [Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems](https://mlsanity.com/paper/2505.17968/) (2025)
- [Humans and language models diverge when predicting repeating text](https://mlsanity.com/paper/2310.06408/) (2023)
- [In-Context Learning Dynamics with Random Binary Sequences](https://mlsanity.com/paper/2310.17639/) (2023)
- [Meta-Learning Neural Mechanisms rather than Bayesian Priors](https://mlsanity.com/paper/2503.16048/) (2025)
- [A Critical Review of Large Language Models: Sensitivity, Bias, and the Path Toward Specialized AI](https://mlsanity.com/paper/2307.15425/) (2023)
- [From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks](https://mlsanity.com/paper/2405.15164/) (2024)
- [Relational decomposition for program synthesis](https://mlsanity.com/paper/2408.12212/) (2024)
- [Distilling Symbolic Priors for Concept Learning into Neural Networks](https://mlsanity.com/paper/2402.07035/) (2024)
- [Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents](https://mlsanity.com/paper/2602.22523/) (2026)
- [Program-Based Strategy Induction for Reinforcement Learning](https://mlsanity.com/paper/2402.16668/) (2024)
- [No Such Thing as a General Learner: Language models and their dual optimization](https://mlsanity.com/paper/2408.09544/) (2024)
- [Opening the black box of language acquisition](https://mlsanity.com/paper/2402.11681/) (2024)
- [Learning Model Successors](https://mlsanity.com/paper/2502.00197/) (2025)
- [Compositionality and the lexicon in evolutionary semantics](https://mlsanity.com/paper/2606.27228/) (2026)
- [Comment on "Modeling rapid language learning by distilling Bayesian priors into artificial neural networks"](https://mlsanity.com/paper/2608.12974/) (2026)
- [Hypothesis-guided discovery of cognitive algorithms via program refinement](https://mlsanity.com/paper/2610.02523/) (2026)

## Abstract (arXiv)

A major target of linguistics and cognitive science has been to understand what class of learning systems can acquire the key structures of natural language. Until recently, the computational requirements of language have been used to argue that learning is impossible without a highly constrained hypothesis space. Here, we describe a learning system that is maximally unconstrained, operating over the space of all computations, and is able to acquire several of the key structures present natural language from positive evidence alone. The model successfully acquires regular (e.g. (ab)n), context-free (e.g. an bn, x xR), and context-sensitive (e.g. anbncn, anbmcndm, xx) formal languages. Our approach develops the concept of factorized programs in Bayesian program induction in order to help manage the complexity of representation. We show in learning, the model predicts several phenomena empirically observed in human grammar acquisition experiments.