Singular value decomposition (SVD) can be viewed as a method for unsupervised training of a network that associates two classes of events reciprocally by linear connections throug...
—Biasing properly the hypothesis space of a learner has been shown to improve generalization performance. Methods for achieving this goal have been proposed, that range from desi...
Grammars play an important role in many Natural Language Processing (NLP) applications. The traditional approach to creating grammars manually, besides being labor-intensive, has ...
Standard algorithms for template-based information extraction (IE) require predefined template schemas, and often labeled data, to learn to extract their slot fillers (e.g., an ...
The effectiveness of support provided to virtual communities depends strongly on what we know about a particular community of people and in what areas the community needs support....