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.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|