We present TextPro, a suite of modular Natural Language Processing (NLP) tools for analysis of Italian and English texts. The suite has been designed so as to integrate and reuse ...
Emanuele Pianta, Christian Girardi, Roberto Zanoli
Corpus-based methods for natural language processing often use supervised training, requiring expensive manual annotation of training corpora. This paper investigates methods for ...
An information retrieval performance measure that is interpreted as the percent of perfect performance (PPP) can be used to study the effects of the inclusion of specific documen...
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
We formalize higher-order separation logic for a first-order imperative language with procedures and local variables in Isabelle/HOLCF. The assertion language is modeled in such a...