The Shared Logistic Normal Distribution for Grammar Induction

Abstract

We present a shared logistic normal distribution as a Bayesian prior over probabilistic grammar weights. This approach generalizes the similar use of logistic normal distributions [3], enabling soft parameter tying during inference across different multinomials comprising the probabilistic grammar. We show that this model outperforms previous approaches on an unsupervised dependency grammar induction task.

Extracted Key Phrases

1 Figure or Table

Cite this paper

@inproceedings{Cohen2008TheSL, title={The Shared Logistic Normal Distribution for Grammar Induction}, author={Shay B. Cohen and Noah A. Smith}, year={2008} }