@InProceedings{britz-guan-luong:2017:EMNLP2017,
  author    = {Britz, Denny  and  Guan, Melody  and  Luong, Minh-Thang},
  title     = {Efficient Attention using a Fixed-Size Memory Representation},
  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     = {392--400},
  abstract  = {The standard content-based attention mechanism typically used in
	sequence-to-sequence models is computationally expensive as it requires the
	comparison of large encoder and decoder states at each time step. In this work,
	we propose an alternative attention mechanism based on a fixed size memory
	representation that is more efficient. Our technique predicts a compact set of
	K attention contexts during encoding and lets the decoder compute an efficient
	lookup that does not need to consult the memory. We show that our approach
	performs on-par with the standard attention mechanism while yielding inference
	speedups of 20% for real-world translation tasks and more for tasks with longer
	sequences. By visualizing attention scores we demonstrate that our models learn
	distinct, meaningful alignments.},
  url       = {https://www.aclweb.org/anthology/D17-1040}
}