Document-Level Neural Machine Translation with Associated Memory Network

  • JIANG Shu
    Department of Computer Science and Engineering, Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University
  • WANG Rui
    Department of Computer Science and Engineering, Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University
  • LI Zuchao
    Department of Computer Science and Engineering, Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University
  • UTIYAMA Masao
    National Institute of Information and Communications Technology
  • CHEN Kehai
    National Institute of Information and Communications Technology
  • SUMITA Eiichiro
    National Institute of Information and Communications Technology
  • ZHAO Hai
    Department of Computer Science and Engineering, Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University
  • LU Bao-liang
    Department of Computer Science and Engineering, Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University

説明

<p>Standard neural machine translation (NMT) is on the assumption that the document-level context is independent. Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while this work focuses on exploiting detailed document-level context in terms of a memory network. The capacity of the memory network that detecting the most relevant part of the current sentence from memory renders a natural solution to model the rich document-level context. In this work, the proposed document-aware memory network is implemented to enhance the Transformer NMT baseline. Experiments on several tasks show that the proposed method significantly improves the NMT performance over strong Transformer baselines and other related studies.</p>

収録刊行物

参考文献 (22)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ