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 Named Entity Resolution (NER) and Word-Sense Disambiguation (WSD).

A paper describing FRED has been accepted for publication to the Semantic Web Journal by IOS Press (please refer to it in scientific publications).

The documentation about how to use FRED as as a HTTP REST service can be found here. To use FRED from Python get fredlib

Enter a text
Options Namespace Prefix for FRED terms:
Namespace for FRED terms: :
Find relations in Linked Data among recognized named entities
Do word-sense disambiguation
Do word-frame disambiguation
Use FrameNet roles
Always merge discourse referents in case of coreference
Text annotation format
Return the semantic-subgraph only (true by default if "Graphical view" is selected)

Powered by

K~tools Tagme Apache Stanbol C&C tools