Context Gates for Neural Machine Translation

Abstract

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.

Accepted by TACL 2017

References in corpus (3)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Modeling Coverage for Neural Machine Translation
• Document Context Language Models

Cited by in corpus (6)

• Sequential Context Encoding for Duplicate Removal
• Non-Autoregressive Machine Translation with Auxiliary Regularization
• Neural Machine Translation Advised by Statistical Machine Translation
• Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model
• Look-ahead Attention for Generation in Neural Machine Translation
• Incorporating Chinese Radicals Into Neural Machine Translation: Deeper Than Character Level