Abstract. In this paper, we present a novel deformation-aware discriminative model for handwritten digit recognition. Unlike previous approaches our model directly considers image ...
Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...
We present a new approach to stochastic modeling of constraintbased grammars that is based on loglinear models and uses EM for estimation from unannotated data. The techniques are...
Stefan Riezler, Detlef Prescher, Jonas Kuhn, Mark ...
We describe a method of incorporating taskspecific cost functions into standard conditional log-likelihood (CLL) training of linear structured prediction models. Recently introduc...
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...