Log-Linear Weight Optimization Using Discriminative Ridge Regression Method in Statistical Machine Translation

摘要

We present a simple and reliable method for estimating the log-linear weights of a state-of-the-art machine translation system, which takes advantage of the method known as discriminative ridge regression (DRR). Since inappropriate weight estimations lead to a wide variability of translation quality results, reaching a reliable estimate for such weights is critical for machine translation research. For this reason, a variety of methods have been proposed to reach reasonable estimates. In this paper, we present an algorithmic description and empirical results proving that DRR, as applied in a pseudo-batch scenario, is able to provide comparable translation quality when compared to state-of-the-art estimation methods (i.e., MERT [1] and MIRA [2]). Moreover, the empirical results reported are coherent across different corpora and language pairs.