This paper presents a method of automatically constructing information extraction patterns on predicate-argument structures (PASs) obtained by full parsing from a smaller training...
Abstract. Conventional artificial neural network models lack many physiological properties of the neuron. Current learning algorithms are more concerned to computational performanc...
Standard no-internal-regret (NIR) algorithms compute a fixed point of a matrix, and hence typically require O(n3 ) run time per round of learning, where n is the dimensionality of...
Beginning to create the New Oxford English Dictionary database has resulted in the realization that databases for reference texts are unlike those for conventional enterprises. Wh...
The authors present TWIG, a visually grounded wordlearning system that uses its existing knowledge of vocabulary, grammar, and action schemas to help it learn the meanings of new ...