Exploiting Sentential Context for Neural Machine Translation
This work addresses translation quality for users of machine translation systems, but it is incremental as it builds on existing Transformer methods.
The paper tackled the problem of improving neural machine translation by exploiting sentential context, resulting in consistent performance gains over the strong Transformer model on WMT14 benchmarks.
In this work, we present novel approaches to exploit sentential context for neural machine translation (NMT). Specifically, we first show that a shallow sentential context extracted from the top encoder layer only, can improve translation performance via contextualizing the encoding representations of individual words. Next, we introduce a deep sentential context, which aggregates the sentential context representations from all the internal layers of the encoder to form a more comprehensive context representation. Experimental results on the WMT14 English-to-German and English-to-French benchmarks show that our model consistently improves performance over the strong TRANSFORMER model (Vaswani et al., 2017), demonstrating the necessity and effectiveness of exploiting sentential context for NMT.