Word learning and the acquisition of syntactic--semantic overhypotheses

TL;DR

This paper presents a computational model demonstrating how children jointly learn syntax and semantics through inductive biases, effectively capturing language acquisition patterns and showing data-efficient learning in adjective acquisition tasks.

Contribution

It introduces a joint learning model that incorporates syntactic-semantic overhypotheses, aligning with child speech patterns and improving learning efficiency.

Findings

Model accurately reflects child speech patterns.

Inducing biases improves learning efficiency.

Model captures children's behavior in adjective learning.

Abstract

Children learning their first language face multiple problems of induction: how to learn the meanings of words, and how to build meaningful phrases from those words according to syntactic rules. We consider how children might solve these problems efficiently by solving them jointly, via a computational model that learns the syntax and semantics of multi-word utterances in a grounded reference game. We select a well-studied empirical case in which children are aware of patterns linking the syntactic and semantic properties of words --- that the properties picked out by base nouns tend to be related to shape, while prenominal adjectives tend to refer to other properties such as color. We show that children applying such inductive biases are accurately reflecting the statistics of child-directed speech, and that inducing similar biases in our computational model captures children's behavior in a classic adjective learning experiment. Our model incorporating such biases also demonstrates a clear data efficiency in learning, relative to a baseline model that learns without forming syntax-sensitive overhypotheses of word meaning. Thus solving a more complex joint inference problem may make the full problem of language acquisition easier, not harder.