Word learning and the acquisition of syntactic--semantic overhypotheses
This work addresses the challenge of efficient language acquisition for children, though it is incremental as it builds on existing empirical studies and computational models.
The paper tackles the joint problem of learning word meanings and syntactic rules in language acquisition by proposing a computational model that incorporates syntactic-semantic biases, showing that it captures children's behavior in an adjective learning experiment and achieves greater data efficiency compared to a baseline model without such biases.
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.