@InProceedings{rei:2017:Long,
  author    = {Rei, Marek},
  title     = {Semi-supervised Multitask Learning for Sequence Labeling},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {2121--2130},
  abstract  = {We propose a sequence labeling framework with a secondary training objective,
	learning to predict surrounding words for every word in the dataset.
	This language modeling objective incentivises the system to learn
	general-purpose patterns of semantic and syntactic composition, which are also
	useful for improving accuracy on different sequence labeling tasks.
	The architecture was evaluated on a range of datasets, covering the tasks of
	error detection in learner texts, named entity recognition, chunking and
	POS-tagging.
	The novel language modeling objective provided consistent performance
	improvements on every benchmark, without requiring any additional annotated or
	unannotated data.},
  url       = {http://aclweb.org/anthology/P17-1194}
}