Software systems must face two challenges today: growing complexity and increasing parallelism in the underlying computational models. The problem of increased complexity is often...
We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram count...
A unified framework to jointly solve the two problems of localization and synchronization at the same time is presented in this paper. The joint approach is attractive because it ...
The paper describes a new approach using a Conditional Random Fields (CRFs) to extract physical and logical layouts in unconstrained handwritten letters such as those sent by indi...
We investigate energy allocation strategies in image sensor networks for the purpose of maximizing the network operational lifetime. For the application scenarios that we consider...