University of Cambridge > Talks.cam > Computer Laboratory Wednesday Seminars > A Bayesian Approach to Learning the Structure of Human Languages

A Bayesian Approach to Learning the Structure of Human Languages

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Stephen Clark.

Grammar Induction has long been a central challenge of Computational Linguistics. Empirically demonstrating the ability of computational models to automatically learn the syntactic structure of human languages will impact upon both our understanding of how children learn language, and our ability to build sophisticated language technologies. In this talk I will describe our recently developed state-of-the-art approach to syntax induction. Using hierarchical non-parametric Bayesian priors we have created probabilistic models of syntactic part-of-speech and dependency grammar that are able to integrate information across a range of granularities. The promising results achieved by these models indicate that the great challenge of Grammar Induction may not be as intractable as long thought.

This talk is part of the Computer Laboratory Wednesday Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity