Context Gates for Neural Machine Translation

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 on 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 lack of effective control on the influence from source and target contexts, conventional NMT tends to yield fluent but inadequate translations. To address this problem, we propose to use context gates to dynamically control the ratios at which source and target contexts contribute to the generation of target words. In this way, we can enhance the adequacy of NMT while keeping the fluency unchanged. Experiments show that our approach significantly improves upon a standard attention-based NMT system by +2.3 BLEU points.