University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Unsupervised Grammar Induction

Unsupervised Grammar Induction

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

If you have a question about this talk, please contact Shakir Mohamed.

We cover some aspects of grammar induction. We first give some sufficient conditions to learn consistent grammars (nederhof_giatta). Then we review a parameter estimation technique (inside-outside algorithm), and the context constituent model (CCM) by Klein and Manning (klein_manning_CCM).

Additional interesting papers about grammar induction:

CCM_initial (the original version of CCM , conditional model instead of generative model)

dependency_grammar (paper about dependency grammar induction)

scfg1 (synchronous context free grammar induction)

scfg2 (also synchronous context free grammar induction)

This talk is part of the Machine Learning Reading Group @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity