Reliable Language Acquisition from Real Data
Time:Thursday, March 18, 11:30 - 12:30
Place:Interschool Lab
PLEASE NOTE THE CHANGE OF LOCATION:
Abstract:
A child acquires the language of her environment from exposure to example utterances; she has no formal language teaching. Lacking any discerning information, a child is likely to assume that every utterance she hears is grammatical (i.e. a valid example of her target language). This presents the child with two problems:
A child cannot know when she has encountered an error. Any simulation
or explanation of language acquisition should therefore attempt to
learn from every utterance it encounters. In this presentation I will
describe a statistical learning system (which implements the Bayesian
Incremental Parameter Setting (BIPS) algorithm) that is robust to
errors and discuss experiments which demonstrate the ability of such a
system to learn from real child-directed speech.
About the speaker:
Paula Buttery is a Phd student at the Natural Language and Information
Processing Group, Computer Laboratory, University of Cambridge, U.K.
Her interests are in computational models of child language acqusition; in
particular, studying the trade-off between the empiricist and nativist
positions on acquisition, and how varying the detail contained in models
of the Universal Grammar affects the speed and accuracy of language
acquisition in computational simulations.