@InProceedings{cotterell-EtAl:2018:Long,
  author    = {Cotterell, Ryan  and  Naradowsky, Jason  and  Mielke, Sebastian J.  and  Wolf-Sonkin, Lawrence},
  title     = {A Structured Variational Autoencoder for Contextual Morphological Inflection},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {2631--2641},
  abstract  = {Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation. To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm. We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-resource setting, and find improvements of over 10% absolute accuracy in some cases.},
  url       = {http://www.aclweb.org/anthology/P18-1245}
}