Neural Graphical Models over Strings for Principal Parts Morphological Paradigm Completion
Ryan Cotterell, John Sylak-Glassman, Christo Kirov · 2017
Many of the world's languages contain an abundance of inflected forms for each lexeme.A major task in processing such languages is predicting these inflected forms.We develop a novel statistical model for the problem, drawing on graphical modeling 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.