We present a method for dependency grammar induction that utilizes sparse annotations of semantic relations. This induction set-up is attractive because such annotations provide u...
We present a method of grounded word learning that is powerful enough to learn the meanings of first and second person pronouns. The model uses the understood words in an utteran...
A major challenge when attempting to analyze and model large-scale Internet phenomena such as the dynamics of global worm propagation is finding ate abstractions that allow us to ...
Nicholas Weaver, Ihab Hamadeh, George Kesidis, Ver...
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and e...