This Project's

Research Team

Co-ordinators

Researchers

Students


External Collaborators

  • Prof Alan Rector
  • Prof Donia Scott

SWAT: Semantic Web Authoring Tool

Theme: Natural Language Generation
Website: http://mcs.open.ac.uk/nlg/SWAT/index.html
Funding Agency: EPSRC


SWAT is a joint project with the School of Computer Science at the University of Manchester and it aims to open up the semantic web to a wide audience through novel techniques that allow viewing and editing of semantic web representation languages in ordinary natural language, as opposed to the methods currently used, such as source coding or graphical interfaces, which require significant training.

An obstacle to realising the goals of the Semantic Web is that it depends technically on standardised formalisms for representing ontologies and factual data (OWL, RDF) that are inaccessible to most users. SWAT will establish principles for mapping between these formalisms and natural languages (e.g., English), so allowing ontologies and data to be defined and viewed through a transparent medium: interactive texts, generated automatically from the underlying encodings in OWL and RDF.

Main Activities

  • Construction of a web-based domain-independent verbalisation tool that arranges ontological facts as a conveniently-structured English glossary for easy reference. This tool has been taken up by other researchers and used as a control for testing their own (domain-dependent) verbaliser.
  • Construction of a similarly domain-independent editing tool that combines WYSIWYM (What You See Is What You Meant) technology with editing of generated controlled natural language.
  • Construction of another domain-independent tool for generating explanations of entailments.

 

Publications

Click here for SWAT publications.

 

Demos

Click here for SWAT Natural Language Verbaliser Tools.

​Click here for SWAT Controlled Language Editing Tools.