Yet these systems still lag far behind human capabilities, and the success they do have relies on machine-learning methods that learn from very large quantities of human-annotated data (for example, speech data with transcriptions or text labelled with syntactic parse trees).
These resource-intensive methods mean that effective technology is available for only a tiny fraction of the world's 5,000 or more languages, mainly those spoken in large rich countries.
The talk will argue that, in order to solve this problem, we need a better understanding of how humans learn and represent language in our minds, and we need to consider how human-like learning biases can be built into computational systems.
Dr Goldwater will illustrate these ideas using examples from her own research. She will discuss why language is such a difficult problem, what we know about human language learning, and show how her own work has taken inspiration from that to develop better methods for computational language learning.
Watch Dr Sharon Goldwater's Needham lecture
Needham lecture interviews
More about Dr Sharon Goldwater
Sharon is a Reader in the Institute for Language, Cognition and Computation at the University of Edinburgh's School of Informatics. She received her PhD from Brown University, supervised by Mark Johnson, and spent two years as a postdoctoral researcher at Stanford University before moving to Edinburgh.
Her research interests include probabilistic machine-learning approaches to natural language processing (especially unsupervised approaches), computer modelling of language acquisition in children, and computational studies of language use. Dr Goldwater holds a Scholar Award from the James S McDonnell Foundation for her work "Understanding synergies in language acquisition through computational modelling".