Current semi-supervised incremental learning approaches select unlabeled examples with predicted high confidence for model re-training. We show that for many applications this dat...
The scores returned by support vector machines are often used as a confidence measures in the classification of new examples. However, there is no theoretical argument sustaining ...
Classifiers that refrain from classification in certain cases can significantly reduce the misclassification cost. However, the parameters for such abstaining classifiers are ofte...
The development of computer-based devices for music control has created a need to study how spectators understand new performance technologies and practices. As a part of a larger...
Little is known about the impact of politeness in online communities. This project combines deductive and inductive approaches to automatically model linguistic politeness in onli...