Neural LMs learn languages with lower m-local entropy more easily, suggesting a shared sensitivity to local statistical structure with human learners.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Information Locality as an Inductive Bias for Neural Language Models
Neural LMs learn languages with lower m-local entropy more easily, suggesting a shared sensitivity to local statistical structure with human learners.