@InProceedings{lavergne-yvon:2017:EMNLP2017,
  author    = {Lavergne, Thomas  and  Yvon, Fran\c{c}ois},
  title     = {Learning the Structure of Variable-Order CRFs: a finite-state perspective},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {433--439},
  abstract  = {The computational complexity of linear-chain Conditional Random Fields (CRFs)
	makes it difficult to deal with very large label sets and long range
	dependencies. Such situations are not rare and arise when dealing with
	morphologically rich languages or joint labelling tasks. We extend here recent
	proposals to consider variable order CRFs. Using an effective finite-state
	representation of variable-length dependencies, we propose new ways to perform
	feature selection at large scale and report experimental results where we
	outperform strong baselines on a tagging task.},
  url       = {https://www.aclweb.org/anthology/D17-1044}
}