In this paper, we introduce a hybrid search for attention-based neural
machine translation (NMT). A target phrase learned with statistical MT models
extends a hypothesis in the NMT beam search when the attention of the NMT model
focuses on the source words translated by this phrase. Phrases added in this
way are scored with the NMT model, but also with SMT features including
phrase-level translation probabilities and a target language model.
Experimental results on German->English news domain and English->Russian
e-commerce domain translation tasks show that using phrase-based models in NMT
search improves MT quality by up to 2.3% BLEU absolute as compared to a strong
NMT baseline.

本文介绍了一种混合搜索的关注机制神经机器翻译模型，该模型使用机器翻译模型和短语级翻译概率等特征来实现目标短语的波束搜索，结果显示与强 NMT 基准模型相比，使用短语模型搜索可以将机器翻译质量提高达到 2.3% 的 BLEU 绝对值的效果。

利用基于短语的模型在混合搜索中进行神经机器翻译

Neural Machine Translation Leveraging Phrase-based Models in a Hybrid  Search

Most global optimization problems are nonlinear and thus difficult to solve,
and they become even more challenging when uncertainties are present in
objective functions and constraints. This paper provides a new two-stage hybrid
search method, called Eagle Strategy, for stochastic optimization. This
strategy intends to combine the random search using L\'evy walk with the
firefly algorithm in an iterative manner. Numerical studies and results suggest
that the proposed Eagle Strategy is very efficient for stochastic optimization.
Finally practical implications and potential topics for further research will
be discussed.

本文提出了一种名为 Eagle Strategy 的新型两阶段混合搜索方法，以解决非线性的全局优化问题。该方法通过使用 Lévy walker 随机搜索和萤火虫算法相结合的方式迭代搜索。 数字研究和结果表明，所提出的 Eagle Strategy 非常适用于随机优化。 最后讨论了实际的应用和潜在的进一步研究主题。