@inproceedings{dou-etal-2018-exploiting,
    title = "Exploiting Deep Representations for Neural Machine Translation",
    author = "Dou, Zi-Yi  and
      Tu, Zhaopeng  and
      Wang, Xing  and
      Shi, Shuming  and
      Zhang, Tong",
    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/jlcl-multiple-ingestion/D18-1457/",
    doi = "10.18653/v1/D18-1457",
    pages = "4253--4262",
    abstract = "Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of encoder and decoder are leveraged in the subsequent process, which misses the opportunity to exploit the useful information embedded in other layers. In this work, we propose to simultaneously expose all of these signals with layer aggregation and multi-layer attention mechanisms. In addition, we introduce an auxiliary regularization term to encourage different layers to capture diverse information. Experimental results on widely-used WMT14 English-German and WMT17 Chinese-English translation data demonstrate the effectiveness and universality of the proposed approach."
}