Context-Driven Construction Learning

We present a computational model of how partial comprehension of utterances in context may drive the acquisition of children's earliest grammatical constructions. The model aims to satisfy convergent constraints from cognitive linguistics and crosslinguistic developmental evidence within a statistically driven computational framework. We examine how the tight coupling between contextually grounded language comprehension and learning processes can be exploited to improve the model's ability to search the space of possible constructions. In particular, previously learned constructions may not fully account for all contextually perceived mappings between forms and meanings. In the model, these incomplete analyses directly prompt the formation of new relational mappings that bridge the gap. We describe an experiiment applying the model to the acquisition of English verb island constructions and discuss how the model handles more complex examples involving Russian morphological constructions. Together these demonstrate the viability of the overall approach and representational potential of the model.