My primary research interest is in unsupervised learning of linguistic structure, both by humans and by machines. I work mainly with probabilistic (especially Bayesian) models, which are useful for exploring the kinds of structures and constraints that are needed to support linguistic generalizations. Areas I am particularly interested in include:

• Computational models of early language acquisition in humans (phonetics, phonologogy, morphology, and word segmentation).
• Joint learning (of morphology/syntax, phonology/morphology, word segmentation/phonology, prosody/syntax, syntax/semantics, etc).
• Nonparametric Bayesian models as applied to language.
• Rational analysis explanations of adult language processing (e.g., information theoretic accounts) and their implications.

PhD Linguistics, 2007, Brown University

Sharon Goldwater is a Reader (≈ US Associate Professor) in the Institute for Language, Cognition and Computation at the University of Edinburgh's School of Informatics. She worked as a researcher in the Artificial Intelligence Laboratory at SRI International from 1998-2000 before starting her Ph.D. at Brown University, supervised by Mark Johnson. She completed her Ph.D. in 2006 and spent two years as a postdoctoral researcher at Stanford University before moving to Edinburgh. Her current research focuses on unsupervised learning for automatic natural language processing and computer modeling of language
acquisition in children. She is particularly interested in Bayesian approaches to the induction of linguistic structure, ranging from phonemic categories to morphology and syntax.