Products of Random Latent Variable Grammars

10 years 11 months ago
Products of Random Latent Variable Grammars
We show that the automatically induced latent variable grammars of Petrov et al. (2006) vary widely in their underlying representations, depending on their EM initialization point. We use this to our advantage, combining multiple automatically learned grammars into an unweighted product model, which gives significantly improved performance over state-ofthe-art individual grammars. In our model, the probability of a constituent is estimated as a product of posteriors obtained from multiple grammars that differ only in the random seed used for initialization, without any learning or tuning of combination weights. Despite its simplicity, a product of eight automatically learned grammars improves parsing accuracy
Slav Petrov
Added 14 Feb 2011
Updated 14 Feb 2011
Type Journal
Year 2010
Authors Slav Petrov
Comments (0)