: The performance of a statistical machine translation (SMT) system heavily depends on the quantity and quality of the bilingual language resource. However, the pervious work mainl...
We describe a new tagging model where the states of a hidden Markov model (HMM) estimated by unsupervised learning are incorporated as the features in a maximum entropy model. Our...
We consider the task of devising large-margin based surrogate losses for the learning to rank problem. In this learning to rank setting, the traditional hinge loss for structured ...
Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
Genetic Programming (GP) is a method of automatically inducing programs by representing them as parse trees. In theory, programs in any computer languages can be translated to par...