Deep neural networks (DNNs) have provably enhanced the state-of-the-art natural language process (NLP) with their capability of feature learning and representation. As one of the more challenging NLP tasks, neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better than NMT in translation adequacy and word coverage. It is therefore a promising direction to combine the advantages of both NMT and SMT. In this article, we propose a deep neural network--based system combination framework leveraging both minimum Bayes-risk decoding and multi-source NMT, which take as input the N-best outputs of NMT and SMT systems and produce the final translation. In particular, we apply the proposed model to both RNN and self-attention networks with different segmentation granularity. We verify our approach empirically through a series of experiments on resource-rich Chinese⇒English and low-resource English⇒Vietnamese translation tasks. Experimental results demonstrate the effectiveness and universality of our proposed approach, which significantly outperforms the conventional system combination methods and the best individual system output.

中文翻译：

---

基于深度神经网络的机器翻译系统组合

深度神经网络 (DNN) 已证明通过其特征学习和表示能力增强了最先进的自然语言处理 (NLP)。作为更具挑战性的 NLP 任务之一，神经机器翻译 (NMT) 成为一种新的机器翻译方法，与统计机器翻译 (SMT) 相比，它产生的结果更加流畅。但是，在翻译充分性和单词覆盖率方面，SMT 通常优于 NMT。因此，结合 NMT 和 SMT 的优点是一个很有前途的方向。在本文中，我们提出了一种基于深度神经网络的系统组合框架，该框架利用最小贝叶斯风险解码和多源 NMT，将 NMT 和 SMT 系统的 N-best 输出作为输入并产生最终翻译。特别是，我们将提出的模型应用于具有不同分割粒度的 RNN 和自注意力网络。我们通过一系列关于资源丰富的中文⇒英语和低资源英语⇒越南语翻译任务的实验来验证我们的方法。实验结果证明了我们提出的方法的有效性和普遍性，显着优于传统的系统组合方法和最佳的单个系统输出。