Context Gates for Neural Machine Translation
Context Gates for Neural Machine Translation
复制标题
DOI：
10.1162/tacl_a_00048
复制
发表时间：
2016-08
影响因子：
10.9
通讯作者：
Zhaopeng Tu;Yang Liu;Zhengdong Lu;Xiaohua Liu;Hang Li
中科院分区：
文献类型：
--
作者：
Zhaopeng Tu;Yang Liu;Zhengdong Lu;Xiaohua Liu;Hang Li
在神经机器翻译（NMT）中，目标词的生成取决于源上下文和目标上下文。我们发现源语语境直接影响译文的充分性，而译语语境影响译文的流畅性。直观地说，实词的生成应该更多地依赖于源语境，虚词的生成应该更多地依赖于目标语境。由于传统的翻译方法缺乏对源语语境和目的语语境的有效控制，译文往往不通顺，但也存在不足。为了解决这个问题，我们提出了上下文门，动态控制源和目标上下文有助于生成目标词的比例。通过这种方式，我们可以通过更仔细地控制来自上下文的信息流来提高NMT的充分性和流利性。实验表明，我们的方法显着提高了一个标准的基于注意力的NMT系统+2.3 BLEU点。
In neural machine translation (NMT), generation of a target word depends on both source and target contexts. We find that source contexts have a direct impact on the adequacy of a translation while target contexts affect the fluency. Intuitively, generation of a content word should rely more on the source context and generation of a functional word should rely more on the target context. Due to the lack of effective control over the influence from source and target contexts, conventional NMT tends to yield fluent but inadequate translations. To address this problem, we propose context gates which dynamically control the ratios at which source and target contexts contribute to the generation of target words. In this way, we can enhance both the adequacy and fluency of NMT with more careful control of the information flow from contexts. Experiments show that our approach significantly improves upon a standard attention-based NMT system by +2.3 BLEU points.