@inproceedings{shankar-etal-2018-surprisingly,
    title = "Surprisingly Easy Hard-Attention for Sequence to Sequence Learning",
    author = "Shankar, Shiv  and
      Garg, Siddhant  and
      Sarawagi, Sunita",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/D18-1065/",
    doi = "10.18653/v1/D18-1065",
    pages = "640--645",
    abstract = "In this paper we show that a simple beam approximation of the joint distribution between attention and output is an easy, accurate, and efficient attention mechanism for sequence to sequence learning. The method combines the advantage of sharp focus in hard attention and the implementation ease of soft attention. On five translation tasks we show effortless and consistent gains in BLEU compared to existing attention mechanisms."
}