Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks

TL;DR

This paper proposes collocational bootstrapping as a mechanism where word co-occurrence patterns help in learning syntax, specifically subject-verb agreement, supported by neural network simulations and analysis of child-directed language.

Contribution

It introduces the concept of collocational bootstrapping and demonstrates its viability for learning syntactic dependencies from statistical signals in language input.

Findings

Neural networks can robustly learn subject-verb agreement within certain variability ranges.

Child-directed language variability falls within the effective range for collocational bootstrapping.

Results support collocational bootstrapping as a plausible learning strategy for children.

Abstract

In what ways might statistical signals in linguistic input assist with the acquisition of syntax? Here we hypothesize a mechanism called collocational bootstrapping, in which regularities in word co-occurrence patterns can provide cues to syntactic dependencies. We investigate whether this mechanism can support the acquisition of English subject-verb agreement. First, we simulate language acquisition by training neural networks on synthetic datasets that vary in how predictable their subject-verb pairings are. We find that there is a range of variability levels at which these statistical learners robustly learn subject-verb agreement. We then analyze the variability of subject-verb pairings in child-directed language, and we find that the variability in such data falls within the range that supported robust generalization in our computational simulations. Taken together, these results suggest that collocational bootstrapping is a viable learning strategy for the type of input that children receive.