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...
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 describe a method of incorporating taskspecific cost functions into standard conditional log-likelihood (CLL) training of linear structured prediction models. Recently introduc...
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
Many statistical translation models can be regarded as weighted logical deduction. Under this paradigm, we use weights from the expectation semiring (Eisner, 2002), to compute fir...