Overview:

Through collaboration with psycholinguists we are studying possible mechanisms through which children acquire language. Using our state-of-the-art SRL to mimic language-learning processes in children, we are able to control what knowledge sources are available to the learner. With this setup we are able to reproduce findings from child learning experiments, demonstrating the efficacy of psycholinguistic theories in a controlled learning environment.

Details:

A fundamental task in sentence comprehension is to assign semantic roles to sentence constituents. The structure-mapping account proposes that children start with a shallow structural analysis of sentences; children treat the number of nouns in the sentence as a cue to its semantic predicate-argument structure, and represent language experience in an abstract format that permits rapid generalization to new verbs. We are able to test this and related hypotheses via experiments with a system for automatic semantic role labeling trained on child-directed speech (BabySRL). We can mimic learning experiments run on children with our BabySRL using different simple representations of the input (such as explicitly ordered sets of nouns), and see if it matches experimental findings. By studying the base representations and the learning progression that children use for language acquisition, we can improve automatic systems that learn and evolve with increasingly complex language input.

Collaborations: