Browse by topic
Type of publication
Minimum Error-Rate Training in Statistical Machine translation using SVMs. 6th Iberian Conference on Pattern Recognition and Image Analysis, (IbPRIA) LNCS 5524, 2009. pp. 378-385. Springer-Verlag.Different works on training of log-linear interpolation models for statistical machine translation reported performance improvements by optimizing parameters with respect to translation quality, rather than to likelihood oriented criteria. This work presents an alternative minimum error-rate training procedure based on structural support vector machines (SSVMs) for log-linear interpolation models which is not limited to the model scaling factors and needs only few iterations to converge. Experimental results are reported on the Spanish–English Europarl corpus.