STLab from ISTC-CNR has designed some semantic technology tools in the last years. They are referred jointly in this page.
FRED is a tool for automatically producing RDF/OWL ontologies and linked data from natural language sentences. The method is based on Combinatory Categorial Grammar, Discourse Representation Theory, Linguistic Frames, and Ontology Design Patterns. Results are enriched with NER and WSD. A paper describing FRED has been published at EKAW 2012 (please refer to it in scientific publications).
FRED is available as REST service.
Designers: Francesco Draicchio (main developer), Andrea Nuzzolese (main developer), Aldo Gangemi, Valentina Presutti, Diego Reforgiato (main developer)
Sentilo performs sentence-based sentiment analysis. It relies on FRED, a successful machine reader for the Semantic Web, and applies appropriate rules to mine FRED's graphs. It provides two interfaces: one to measure the "sentimeters" of a sentence, the other to visualize a semantic graph representation of a sentence enriched with opinion-related information, e.g. opinion holder, topics, sentiment scores, etc. Sentilo is available as a REST service that returns RDF as output.
Designers: Diego Reforgiato (main developer),
Andrea Nuzzolese (main developer), Sergio Consoli (main developer), Aldo Gangemi, Valentina Presutti.
Tìpalo uses FRED and automatically assigns types to Wikipedia entities. Given a Wikipedia page URI, the tool returns an RDF graph composed of rdf:type, rdfs:subClassOf, owl:sameAs, and owl:equivalentTo statements providing typing information about the entity referred by the Wikipedia page.
Tìpalo is available as REST service.
Designers: Francesco Draicchio, Aldo Gangemi, Alberto Musetti, Andrea G. Nuzzolese (main developer), Valentina Presutti.
Aemoo helps exploring Wikipedia knowledge in a twofold way. It implements filtering strategies based on Encyclopedic Knowledge Patterns (EKP), which have been extracted from the Wikipedia linking structure, showing alternatively "core" or "curious" knowledge about a Wikipedia entity. A paper on EKP, and another paper on Aemoo.
Designers: Francesco Draicchio, Aldo Gangemi, Alberto Musetti (main developer), Andrea Nuzzolese (main developer), Valentina Presutti.
RelNet is a novel Web tool used to align a user-supplied property to existing Semantic Web relations retrieved from different vocabulary repositories (Watson, Linked Open Vocabularies (LOV), and Never-Ending Language Learning (NELL)). The aim is to provide easy access to the ecosystem of vocabularies in the growing Linked Data Web in search of a specific property supplied by the user, providing metrics on how the matching properties are used in the LOD cloud, helping to improve their understanding, visibility and usability, and overall quality.
Designers: Andrea Nuzzolese (main developer), Sergio Consoli (main developer), Diego Reforgiato (main developer), Valentina Presutti, Aldo Gangemi.
Legalo is a novel Open Knowledge Extraction approach that performs unsupervised, open domain, and abstractive knowledge extraction from text for producing directly usable machine readable information. The method is based on the hypothesis that hyperlinks (either created by humans or knowledge extraction tools) provide a pragmatic trace of semantic relations between two entities, and that such semantic relations, their subjects and objects, can be revealed by processing their linguistic traces (i.e. the sentences that embed the hyperlinks) and formalised as Semantic Web triples and ontology axioms. Given an English sentence as input, Legalo produces a set of RDF triples representing relevant factual relations expressed in the sentence, the predicates of which are formally defined in terms of OWL axioms.
Legalo is based on a pipeline of components which relies on FRED to transform natural language text into a formal RDF/OWL graph representation.
Semantic Web binary relations that capture the semantics of the specific relations are then extracted from FRED graphs by using a set of graph pattern-based rules. When possible, Legalo aligns the produced properties to others already existing in the Semantic Web with our service RelNet, by using different Web resources available online: Watson, Linked Open Vocabularies (LOV), and Never-Ending Language Learning (NELL). Legalo is available as a REST service returning RDF as output.
Designers: Andrea Nuzzolese (main developer), Sergio Consoli (main developer), Diego Reforgiato (main developer), Valentina Presutti, Aldo Gangemi.
Legalo - Wikipedia is a deployment of the Legalo service on Wikipedia pages, aimed at showing the potential impact of the system on Linked Open Data population. It takes as input any user-defined Wikipedia entity, and produces as output the RDF binary properties synthesizing the semantic relations conveyed by any Wikipedia Pagelinks embedded in the correspondent Wikipedia page of the given entity.
Designers: Andrea Nuzzolese (main developer), Sergio Consoli (main developer), Diego Reforgiato (main developer), Valentina Presutti, Aldo Gangemi.
Wikifier resolves arbitrary named entities (i.e. either individuals or concepts) on Wikipedia. See Wikifier page for details on its parametrization and implemented method.
Designers: Concetto Elvio Bonafede (main developer), Aldo Gangemi, Alfio Gliozzo.
Ditto (Digrams Transformation into OWL) is a tool that enables the automatic transformation of E/R diagrams with crow's foot notation developed in yEd into OWL ontologies, according to three different transformation schemes.
Designers: Aldo Gangemi, Silvio Peroni (main developer).
XDTools is a plugin to the NeOn Toolkit and provides a perspective - eXtreme Design - that groups components for ontology design: the ODP Registry browser and ODP Details view, the XD Selector, the XD Specialization Wizard, the XD Analyzer and the XD Annotation dialog. Information on its page.
Designers: Eva Blomqvist, Enrico Daga (main developer), Aldo Gangemi, Valentina Presutti.
The SemanticScout is a graphical exploratory browser to data.cnr.it, the linked data from the Italian National Research Council (CNR), developed jointly with the Information Systems Unit of CNR. Try it from its main page or directly from data.cnr.it.
Designers: Enrico Daga (main developer), Aldo Gangemi, Alberto Salvati, Gianluca Troiani. With the collaboration of Claudio Baldassarre and Alfio Gliozzo.
STLab members substantially contribute to Apache Stanbol: a library of components for extending traditional content management systems with semantic services. See the Stanbol web site for details and documentation.
Kali-ma is a plugin for the NeOn Toolkit that provides a unified view for browsing and accessing the ontology design functionalities provided by the other plugins on a specific NeOn Toolkit installation.
It also provides a realtime chat functionality integrated with local ontology projects, and a search service for ontology project metadata injected by the Toolkit or its plugins. More information on its page, or watch a screencast.
Designers: Alessandro Adamou (main developer), Aldo Gangemi, Valentina Presutti.
Feedback and info: stlab@cnr.it
