Abstract
AbstractAutomated, data-driven construction and evaluation of scientific models and theories is a long-standing challenge in artificial intelligence. We present a framework for algorithmically synthesizing models of a basic part of human language: morpho-phonology, the system that builds word forms from sounds. We integrate Bayesian inference with program synthesis and representations inspired by linguistic theory and cognitive models of learning and discovery. Across 70 datasets from 58 diverse languages, our system synthesizes human-interpretable models for core aspects of each language’s morpho-phonology, sometimes approaching models posited by human linguists. Joint inference across all 70 data sets automatically synthesizes a meta-model encoding interpretable cross-language typological tendencies. Finally, the same algorithm captures few-shot learning dynamics, acquiring new morphophonological rules from just one or a few examples. These results suggest routes to more powerful machine-enabled discovery of interpretable models in linguistics and other scientific domains.
Publisher
Springer Science and Business Media LLC
Subject
General Physics and Astronomy,General Biochemistry, Genetics and Molecular Biology,General Chemistry,Multidisciplinary
Reference53 articles.
1. Godfrey-Smith, P. Theory and Reality: An Introduction to the Philosophy of Science (University of Chicago Press, 2009).
2. Gerstenberg, T. & Tenenbaum, J. B. In Intuitive Theories. Oxford Handbook of Causal Reasoning 515–548 (Oxford University Press, 2017).
3. Carey, S. Conceptual Change in Childhood (MIT Press, 1985).
4. Schulz, L. The origins of inquiry: inductive inference and exploration in early childhood. Trends Cogn. Sci. 16, 382–389 (2012).
5. Gopnik, A., Meltzoff, A. N. & Kuhl, P. K. The Scientist in the Crib: Minds, Brains, and How Children Learn (William Morrow & Co, 1999).
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献