FORGe at WebNLG 2017

Simple item page
dc.contributor.authorMille, Simonca
dc.contributor.authorDasiopoulou, Stamatiaca
dc.date.accessioned2018-04-06T17:54:08Z
dc.date.available2018-04-06T17:54:08Z
dc.date.issued2017
dc.description.abstractThis paper describes the FORGe generator at E2E. The input triples are mapped onto sentences by applying a series of rule-based graph-transducers and aggregation grammars to template predicate-argument structures associated to each property. We submitted two primary systems to the task, one based on the grammars, and one based on templates, and one secondary system, which is a variation of the grammar-based one.en
dc.format.mimetypeapplication/pdf
dc.identifier.citationMille S, Dasiopoulou S. FORGe at WebNLG 2017. Barcelona: Universitat Pompeu Fabra. Department of Information and Communications Technologies, 2017. Report No.: 17-09.
dc.identifier.urihttp://hdl.handle.net/10230/34306
dc.language.isoeng
dc.publisherUniversitat Pompeu Fabraca
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/645012
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.titleFORGe at WebNLG 2017ca
dc.typeinfo:eu-repo/semantics/workingPaper
dc.type.versioninfo:eu-repo/semantics/publishedVersion

Files

Collections