Incrementally Updating the SMT Reordering Model

This work is concerned with incrementally training statistical machine translation (SMT) models when new data becomes available. That, in contrast to re-training new models based on the entire accumulated data. Incremental training provides a way to perform faster, more frequent model updates, enabling keeping the SMT system up-to-date with the most recent data. Specifically, we address incrementally updating the reordering model (RM), a component in phrase-based machine translation that models phrase order changes between the source and the target languages, and for which incremental training has not been proposed so far. First, we show that updating the reordering model is helpful for improving translation quality. Second, we present an algorithm for updating the reordering model within the popular Moses SMT system. Our method produces the exact same model as when training the model from scratch, but doing so much faster.