We present the methodology that underlies new metrics for semantic machine translation evaluation that we are developing. Unlike widely-used lexical and n-gram based MT evaluation...
Independent component analysis (ICA) is a statistical and computational technique for revealing hidden factors that underlie sets of signals. We propose an improved ICA framework ...
Jing Sui, Jingyu Liu, Lei Wu, Andrew Michael, Lai ...
Previous work showed that statistical analysis techniques could successfully be used to construct compact signatures of distinct operational problems in Internet server systems. B...
Several tools and methods for source code quality assurance based on static analysis finally reached a state when they are applicable in practice and recognized by the industry. H...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...