We propose one geometric algorithm to solve both the problem of circularity test and the problem of circularity measure. The former problem consists in deciding whether a given di...
In this paper, we present a new decompositional approach for the extraction of propositional rules from feed-forward neural networks of binary threshold units. After decomposing t...
Abstract. This paper presents how text summarization can be influenced by textual entailment. We show that if we use textual entailment recognition together with text summarization...
Quality is an open concept. Something has a good quality when the most salient of its characteristics have a positive value. What are this relevant features? It depends on the int...
Patrizia Ghislandi, Anna Pedroni, Daniela Paolino,...
We show how to use unlabeled data and a deep belief net (DBN) to learn a good covariance kernel for a Gaussian process. We first learn a deep generative model of the unlabeled da...