Traditional scenario of probabilistic modelling is directed at generating samples having a given probability distribution. We argue that this scenario is impracticable for image m...
We describe computationally efficient methods for learning mixtures in which each component is a directed acyclic graphical model (mixtures of DAGs or MDAGs). We argue that simple...
Bo Thiesson, Christopher Meek, David Maxwell Chick...
Computational models of meaning trained on naturally occurring text successfully model human performance on tasks involving simple similarity measures, but they characterize meani...
Marco Baroni, Brian Murphy, Eduard Barbu, Massimo ...
At the early stages of the phagocytic signalling, Rho GTP-binding proteins play a key role. With the stimulus from the cell membrane and with the help from the regulators (GEF, GA...
We present a global joint model for lemmatization and part-of-speech prediction. Using only morphological lexicons and unlabeled data, we learn a partiallysupervised part-of-speec...