Target-Side Context for Discriminative Models in Statistical Machine Translation
This work addresses translation quality for machine translation systems, but it is incremental as it builds on existing source-context models.
The paper tackled the problem of improving statistical machine translation by extending discriminative models to incorporate target-side context, resulting in consistent translation quality improvements across four language pairs.
Discriminative translation models utilizing source context have been shown to help statistical machine translation performance. We propose a novel extension of this work using target context information. Surprisingly, we show that this model can be efficiently integrated directly in the decoding process. Our approach scales to large training data sizes and results in consistent improvements in translation quality on four language pairs. We also provide an analysis comparing the strengths of the baseline source-context model with our extended source-context and target-context model and we show that our extension allows us to better capture morphological coherence. Our work is freely available as part of Moses.