Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks
For researchers in language acquisition and computational linguistics, this work offers a hypothesis about how statistical cues in input might aid syntactic learning, though it is an incremental contribution building on existing ideas.
The paper proposes collocational bootstrapping as a mechanism for learning subject-verb agreement, showing through neural network simulations that statistical regularities in word co-occurrence can support acquisition, and that child-directed language exhibits variability within the range that enables robust learning.
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.