Production of parallel training corpora for the development of statistical machine translation (SMT) systems for resource-poor languages usually requires extensive manual effort. ...
Active learning has been proven a reliable strategy to reduce manual efforts in training data labeling. Such strategies incorporate the user as oracle: the classifier selects the m...
Web site development method is at an early stage in its evolution. Most existing methods are concerned with technical software issues and are poorly adapted to help developers thi...
Interactively learning from a small sample of unlabeled examples is an enormously challenging task, one that often arises in vision applications. Relevance feedback and more recen...
ShyamSundar Rajaram, Charlie K. Dagli, Nemanja Pet...
We introduce an algorithm that, given n objects, learns a similarity matrix over all n2 pairs, from crowdsourced data alone. The algorithm samples responses to adaptively chosen t...
Omer Tamuz, Ce Liu, Serge Belongie, Ohad Shamir, A...