Execution and communication traces are central to performance modeling and analysis. Since the traces can be very long, meaningful compression and extraction of representative beha...
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
In recent years, matrix approximation for missing value prediction has emerged as an important problem in a variety of domains such as recommendation systems, e-commerce and onlin...
Morphologically rich languages pose a challenge to the annotators of treebanks with respect to the status of orthographic (spacedelimited) words in the syntactic parse trees. In s...
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...