@InProceedings{hewlett-EtAl:2017:EMNLP2017,
  author    = {Hewlett, Daniel  and  Jones, Llion  and  Lacoste, Alexandre  and  gur, izzeddin},
  title     = {Accurate Supervised and Semi-Supervised Machine Reading for Long Documents},
  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     = {2011--2020},
  abstract  = {We introduce a hierarchical architecture for machine reading capable of
	extracting precise information from long documents.
	The model divides the document into small, overlapping windows and encodes all
	windows in parallel with an RNN.
	It then attends over these window encodings, reducing them to a single
	encoding, which is decoded into an answer using a sequence decoder.
	This hierarchical approach allows the model to scale to longer documents
	without increasing the number of sequential steps.
	In a supervised setting, our model achieves state of the art accuracy of 76.8
	on the WikiReading dataset.
	We also evaluate the model in a semi-supervised setting by downsampling the
	WikiReading training set to create increasingly smaller amounts of supervision,
	while leaving the full unlabeled document corpus to train a sequence
	autoencoder on document windows.
	We evaluate models that can reuse autoencoder states and outputs without
	fine-tuning their weights, allowing for more efficient training and inference.},
  url       = {https://www.aclweb.org/anthology/D17-1214}
}