Active learning reduces the amount of manually annotated sentences necessary when training state-ofthe-art statistical parsers. One popular method, uncertainty sampling, selects sentences for which the parser exhibits low certainty. However, this method does not quantify confidence about the current statistical model itself. In particular, we should be less confident about selection decisions b...

We now will apply the tools and concepts of thermodynamics and probability which we introduced in Chapters 2 and 3 to relate the microscopic and macroscopic descriptions of thermal systems. In so doing we will develop the formalism of statistical mechanics. To make explicit the probabilistic assumptions and the type of calculations that are done in statistical mechanics we first discuss an isol...

In this work, we investigate Batch Normalization technique and propose its probabilistic interpretation. We propose a probabilistic model and show that Batch Normalization maximazes the lower bound of its marginalized log-likelihood. Then, according to the new probabilistic model, we design an algorithm which acts consistently during train and test. However, inference becomes computationally in...