We use a generative history-based model to predict the most likely derivation of a dependency parse. Our probabilistic model is based on Incremental Sigmoid Belief Networks, a rec...
A probabilistic, ``neural'' approach to sensor modelling and classification is described, performing local data fusion in a wireless system for embedded sensors using a ...
Abstract. Nowadays, digital libraries are inherently dispersed over several peers of a steadily increasing network. Dedicated peers may provide specialized, computationally expensi...
In order to manage and enforce multiple heterogeneous authorization policies in distributed authorization environment, we defined the root policy specification language and its cor...
In this paper, we propose a novel discriminative language model, which can be applied quite generally. Compared to the well known N-gram language models, discriminative language m...