Discriminative ridge regression algorithm for adaptation in statistical machine translation

Abstract

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 is able to provide comparable translation quality when compared to state-of-the-art estimation methods [i.e. MERT (Och in Proceedings of the annual meeting of the association for computational linguistics, 2003) and MIRA (Cherry and Foster in Proceedings of the North American chapter of the association for computational linguistics, 2012)], with a reduction in computational cost. Moreover, the empirical results reported are coherent across different corpora and language pairs.