International Workshop on Spoken Language Translation (IWSLT) 2009
Minimum error rate training (MERT) is a widely used learning method for statistical machine translation. In this paper, we present a SVM-based training method to enhance generalization ability. We extend MERT optimization by maximizing the margin between the reference and incorrect translations under the L2-norm prior to avoid overfitting problem. Translation accuracy obtained by our proposed methods is more stable in various conditions than that obtained by MERT. Our experimental results on the French- English WMT08 shared task show that degrade of our proposed methods is smaller than that of MERT in case of small training data or out-of-domain test data.
Full Paper Presentation (pdf)
Bibliographic reference. Hayashi, Katsuhiko / Watanabe, Taro / Tsukada, Hajime / Isozaki, Hideki (2009): "Structural support vector machines for log-linear approach in statistical machine translation", In IWSLT-2009, 144-151.