Roberto Prevete

Learn More
Answer Validation is an emerging topic in Question Answering, where open domain systems are often required to rank huge amounts of candidate answers. We present a novel approach to answer validation based on the intuition that the amount of implicit knowledge which connects an answer to a question can be quantitatively estimated by exploiting the redundancy(More)
This paper presents the DIOGENE question/answering system developed at ITC-Irst. The system is based on a rather standard architecture which includes three components for question processing, search and answer extraction. Linguistic processing strongly relies onMULTIWORDNET,anextendedversionofthe English WORDNET. The system has been designed to address two(More)
This paper presents a new version of the DIOGENE Question Answering (QA) system developedd at ITC-Irst.. Withh respect too our first participationn too the TREC QA m ainn task (TREC-2001),, the system presents bothh improvements andd extensions.. Onn one hand,, significant improvements r ely onn the substitutionn of basic components (e.g. the searchh engine(More)
This paper addresses the problem of extracting view-invariant visual features for the recognition of object-directed actions and introduces a computational model of how these visual features are processed in the brain. In particular, in the test-bed setting of reach-to-grasp actions, grip aperture is identified as a good candidate for inclusion into a(More)
This paper presents an innovative approach to the automatic evaluation of Question Answering systems. The methodology relies on the use of the Web, considered as an " oracle " containing all the information needed to check the relevance of a candidate answer with respect to a given question. The procedure is completely automatic (i.e. no human intervention(More)
Typical patterns of hand-joint covariation arising in the context of grasping actions enable one to provide simplified descriptions of these actions in terms of small sets of hand-joint parameters. The computational model of mirror mechanisms introduced here hypothesizes that mirror neurons are crucially involved in coding and making this simplified motor(More)
Target behaviours can be achieved by finding suitable parameters for Continuous Time Recurrent Neural Networks (CTRNNs) used as agent control systems. Differential Evolution (DE) has been deployed to search parameter space of CTRNNs and overcome granularity, boundedness and blocking limitations. In this paper we provide initial support for DE in the context(More)