@inproceedings{hayashi-etal-2009-structural,
    title = "Structural support vector machines for log-linear approach in statistical machine translation",
    author = "Hayashi, Katsuhiko  and
      Watanabe, Taro  and
      Tsukada, Hajime  and
      Isozaki, Hideki",
    booktitle = "Proceedings of the 6th International Workshop on Spoken Language Translation: Papers",
    month = dec # " 1-2",
    year = "2009",
    address = "Tokyo, Japan",
    url = "https://preview.aclanthology.org/build-pipeline-with-new-library/2009.iwslt-papers.3/",
    pages = "144--151",
    abstract = "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."
}