@article{tu-etal-2018-learning,
    title = "Learning to Remember Translation History with a Continuous Cache",
    author = "Tu, Zhaopeng  and
      Liu, Yang  and
      Shi, Shuming  and
      Zhang, Tong",
    editor = "Lee, Lillian  and
      Johnson, Mark  and
      Toutanova, Kristina  and
      Roark, Brian",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "6",
    year = "2018",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/ingest-emnlp/Q18-1029/",
    doi = "10.1162/tacl_a_00029",
    pages = "407--420",
    abstract = "Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information. In this work, we propose to augment NMT models with a very light-weight cache-like memory network, which stores recent hidden representations as translation history. The probability distribution over generated words is updated online depending on the translation history retrieved from the memory, endowing NMT models with the capability to dynamically adapt over time. Experiments on multiple domains with different topics and styles show the effectiveness of the proposed approach with negligible impact on the computational cost."
}