We describe a method for learning steerable deformable part models. Our models exploit the fact that part templates can be written as linear filter banks. We demonstrate that one...
We show that the standard beam-search algorithm can be used as an efficient decoder for the global linear model of Zhang and Clark (2008) for joint word segmentation and POS-taggi...
In this paper, we propose a novel method for rapid feature space Maximum Likelihood Linear Regression (FMLLR) speaker adaptation based on bilinear models. When the amount of adapt...
With the rise of XML as a standard model of data exchange, XML functional dependencies (XFDs) have become important to areas such as key analysis, document normalization, and data ...
Text clustering is most commonly treated as a fully automated task without user supervision. However, we can improve clustering performance using supervision in the form of pairwi...