A latent variable model for generative dependency parsing

Abstract

We propose a generative dependency parsing model which uses binary latent variables to induce conditioning features. To define this model we use a recently proposed class of Bayesian Networks for structured prediction, Incremental Sigmoid Belief Networks. We demonstrate that the proposed model achieves state-of-the-art results on three different languages. We also demonstrate that the features induced by the ISBN’s latent variables are crucial to this success, and show that the proposed model is particularly good on long dependencies.