资源分类
》 资源 》论文》Depth Growing for Neural Machine Translation

Depth Growing for Neural Machine Translation

2019-09-19 | |  75 |   47 |   0 0 0
Abstract While very deep neural networks have shown effectiveness for computer vision and text classification applications, how to increase the network depth of neural machine translation (NMT) models for better translation quality remains a challenging problem. Directly stacking more blocks to the NMT model results in no improvement and even reduces performance. In this work, we propose an effective two-stage approach with three specially designed components to construct deeper NMT models, which result in significant improvements over the strong Transformer baselines on WMT14 English?German and English?French translation tasks.

上一篇：Bridging the Gap between Training and Inference for Neural Machine Translation

下一篇：Domain Adaptation of Neural Machine Translation by Lexicon Induction

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...