The basic concept in Neural Machine Translation (NMT) is to train a large
Neural Network that maximizes the translation performance on a given parallel
corpus. NMT is then using a simple left-to-right beam-search decoder to
generate new translations that approximately maximize the trained conditional
probability. The current beam search strategy generates the target sentence
word by word from left-to- right while keeping a fixed amount of active
candidates at each time step. First, this simple search is less adaptive as it
also expands candidates whose scores are much worse than the current best.
Secondly, it does not expand hypotheses if they are not within the best scoring
candidates, even if their scores are close to the best one. The latter one can
be avoided by increasing the beam size until no performance improvement can be
observed. While you can reach better performance, this has the draw- back of a
slower decoding speed. In this paper, we concentrate on speeding up the decoder
by applying a more flexible beam search strategy whose candidate size may vary
at each time step depending on the candidate scores. We speed up the original
decoder by up to 43% for the two language pairs German-English and
Chinese-English without losing any translation quality.

本文提出了通过改进灵活的 beam-search decoder 来加速神经机器翻译的方法，并测试表明，该方法可以提高速度，同时不影响翻译质量。

神经机器翻译的束搜索策略

Beam Search Strategies for Neural Machine Translation

We investigate the use of hierarchical phrase-based SMT lattices in
end-to-end neural machine translation (NMT). Weight pushing transforms the
Hiero scores for complete translation hypotheses, with the full translation
grammar score and full n-gram language model score, into posteriors compatible
with NMT predictive probabilities. With a slightly modified NMT beam-search
decoder we find gains over both Hiero and NMT decoding alone, with practical
advantages in extending NMT to very large input and output vocabularies.

本文研究了使用分层短语配对 SMT 网络在端到端的神经机器翻译（NMT）中的应用。通过权重推送将完整的翻译预测假设的 Hiero 分数，包括完整的翻译语法分数和完整的 n-gram 语言模型分数，转换为与 NMT 预测概率兼容的后验概率，并通过稍加修改的 NMT 波束搜索解码器，发现了比 Hiero 和 NMT 单独解码的改进，在扩展 NMT 到非常大的输入和输出词汇方面具有实际优势。