We achieved a state of the art performance in statistical machine translation by using a large number of features with an online large-margin training algorithm. The millions of p...
Taro Watanabe, Jun Suzuki, Hajime Tsukada, Hideki ...
Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation estimates and low coverage over source and target p...
Neuroimaging datasets often have a very large number of voxels and a very small number of training cases, which means that overfitting of models for this data can become a very se...
Tanya Schmah, Geoffrey E. Hinton, Richard S. Zemel...
The extensive work on Knowledge Engineering in the 1990s has resulted in a systematic analysis of task-types, and the corresponding problem solving methods that can be deployed fo...
Frank van Harmelen, Annette ten Teije, Holger Wach...
Systems that learn from examples often create a disjunctive concept definition. Small disjuncts are those disjuncts which cover only a few training examples. The problem with sma...