Discriminative translation models utilizing source context have been shown to help statistical machine translation performance. In this talk, I will describe a novel extension of this work using target context information. I will show how this model can be efficiently integrated directly in the decoding process of a phrase-based translation system. I will present results which validate that our approach scales to large training data sizes and results in consistent improvements in translation quality on four language pairs. I will also provide an analysis comparing the strengths of the baseline source-context model with our extended source-context and target-context model.