@InProceedings{martins-kreutzer:2017:EMNLP2017,
  author    = {Martins, Andr\'{e} F. T.  and  Kreutzer, Julia},
  title     = {Learning What's Easy: Fully Differentiable Neural Easy-First Taggers},
  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     = {349--362},
  abstract  = {We introduce a novel neural easy-first decoder that learns to solve sequence
	tagging tasks in a flexible order. In contrast to previous easy-first decoders,
	our models are end-to-end differentiable. The decoder iteratively updates a
	“sketch” of the predictions over the sequence. At its core is an attention
	mechanism that controls which parts of the input are strategically the best to
	process next. We present a new constrained softmax transformation that ensures
	the same cumulative attention to every word, and show how to efficiently
	evaluate and backpropagate over it. Our models compare favourably to BILSTM
	taggers on three sequence tagging tasks.},
  url       = {https://www.aclweb.org/anthology/D17-1036}
}