Semantic Web Machine Reading with FRED

Article type: Research Article

Authors: Gangemi, Aldo^{a; b; *} | Presutti, Valentina^b | Reforgiato Recupero, Diego^b | Nuzzolese, Andrea Giovanni^b | Draicchio, Francesco^b | Mongiovì, Misael^b

Affiliations: [a] LIPN, Université Paris 13, Sorbonne Paris Cité CNRS UMR 7030, France. E-mail: aldo.gangemi@lipn.univ-paris13.fr | [b] Semantic Technology Lab, ISTC-CNR, Rome and Catania, Italy. E-mails: aldo.gangemi@istc.cnr.it, valentina.presutti@istc.cnr.it, diego.reforgiato@istc.cnr.it, andrea.nuzzolese@istc.cnr.it, misael.mongiovi@istc.cnr.it

Correspondence: [*] Corresponding author. E-mail: aldo.gangemi@lipn.univ-paris13.fr.

Abstract: A formal machine reader is a tool able to transform natural language text into formal structured knowledge so as the latter can be interpreted by machines, according to a shared semantics. FRED is a formal machine reader for the semantic web: its output is a RDF/OWL graph, whose design is based on frame semantics. FRED’s graph are domain- and task-independent, making the tool suitable to be used as a semantic middleware for domain- or task-specific applications. To serve this purpose, it is available both as REST service and as Python library. This paper provides details about FRED’s capabilities, design issues, implementation and evaluation.

Keywords: Machine reading, knowledge extraction, Semantic Web, Linked Data, event extraction

DOI: 10.3233/SW-160240

Journal: Semantic Web, vol. 8, no. 6, pp. 873-893, 2017