We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
The web contains lots of interesting factual information about entities, such as celebrities, movies or products. This paper describes a robust bootstrapping approach to corrobora...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
An ever greater range of applications call for learning from sequences. Grammar induction is one prominent tool for sequence learning, it is therefore important to know its proper...
Most commonly used inductive rule learning algorithms employ a hill-climbing search, whereas local pattern discovery algorithms employ exhaustive search. In this paper, we evaluat...