Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...
Statistical user simulation is an efficient and effective way to train and evaluate the performance of a (spoken) dialog system. In this paper, we design and evaluate a modular da...
An approach to the deformable registration of three-dimensional brain tumor images to a normal brain atlas is presented. The approach involves the integration of three components:...
like text summarisation requires a means of producing novel summary sentences. In order to improve the grammaticality of the generated sentence, we model a global (sentence) level...
In this work we present two extensions to the well-known dynamic programming beam search in phrase-based statistical machine translation (SMT), aiming at increased efficiency of ...