Many of the world's languages contain an abundance of inflected forms for each lex eme. A major task in processing such lan guages is predicting these inflected forms. We develop a novel statistical model for the problem, drawing on graphical model ing techniques and recent advances in deep learning. We derive a Metropolis-Hastings algorithm to jointly decode the model. Our Bayesian network draws inspiration from principal parts morphological analysis. We demonstrate improvements on 5 languages.
展开▼