Neural Graphical Models over Strings for Principal Parts Morphological Paradigm Completion

Ryan Cotterell, John Sylak-Glassman, Christo Kirov


Abstract
Many of the world’s languages contain an abundance of inflected forms for each lexeme. A critical 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.
Anthology ID:
E17-2120
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
759–765
Language:
URL:
https://www.aclweb.org/anthology/E17-2120
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/E17-2120.pdf