Modelling Child Learning and Parsing of Long-range Syntactic Dependencies
This addresses the problem of understanding how children acquire complex language structures, but it is incremental as it builds on existing probabilistic models.
The authors developed a probabilistic child language acquisition model that learns word meanings and syntax from real child-directed speech, successfully deducing parse trees and meanings, including for long-range syntactic dependencies like object wh-questions.
This work develops a probabilistic child language acquisition model to learn a range of linguistic phenonmena, most notably long-range syntactic dependencies of the sort found in object wh-questions, among other constructions. The model is trained on a corpus of real child-directed speech, where each utterance is paired with a logical form as a meaning representation. It then learns both word meanings and language-specific syntax simultaneously. After training, the model can deduce the correct parse tree and word meanings for a given utterance-meaning pair, and can infer the meaning if given only the utterance. The successful modelling of long-range dependencies is theoretically important because it exploits aspects of the model that are, in general, trans-context-free.