Synthesizing theories of human language with Bayesian program induction
Name
s41467-022-32012-w.pdf
Description
Published version
Size
2.19 MB
Format
Adobe PDF
Checksum (MD5)
bbd32a08fee3ed2607e1a58f796c51e0
Author(s)
Ellis, Kevin
Albright, Adam
Solar-Lezama, Armando
Tenenbaum, Joshua B
O’Donnell, Timothy J
Date Issued
2022
Journal
Nature Communications
Publisher
Springer Science and Business Media LLC
Citation
Ellis, Kevin, Albright, Adam, Solar-Lezama, Armando, Tenenbaum, Joshua B and O’Donnell, Timothy J. 2022. "Synthesizing theories of human language with Bayesian program induction." Nature Communications, 13 (1).
Version
Final published version
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.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1038/S41467-022-32012-W
