Please use this identifier to cite or link to this item: https://hdl.handle.net/10316/115592
DC FieldValueLanguage
dc.contributor.authorFaria, Bruno-
dc.contributor.authorPerdigão, Dylan-
dc.contributor.authorOliveira, Hugo Gonçalo-
dc.date.accessioned2024-07-16T21:50:51Z-
dc.date.available2024-07-16T21:50:51Z-
dc.date.issued2023-10-15-
dc.identifier.urihttps://hdl.handle.net/10316/115592-
dc.description.abstractThis paper explores GPT-3 for answering natural language questions over Linked Data. Different engines of the model and different approaches are adopted for answering questions in the QALD-9 dataset, namely: zero and few-shot SPARQL generation, as well as fine-tuning in the training portion of the dataset. Answers retrieved by the generated queries and answers generated directly by the model are also compared. Overall results are generally poor, but several insights are provided on using GPT-3 for the proposed task.pt
dc.language.isoengpt
dc.publisherSchloss Dagstuhl – Leibniz-Zentrum für Informatikpt
dc.relationC645008882-00000055pt
dc.rightsopenAccesspt
dc.subjectSPARQL Generationpt
dc.subjectPrompt Engineeringpt
dc.subjectFew-Shot Learningpt
dc.subjectQuestion Answeringpt
dc.subjectGPT-3pt
dc.titleQuestion Answering over Linked Data with GPT-3pt
dc.typebookPartpt
degois.publication.firstPage1pt
degois.publication.lastPage15pt
degois.publication.location12th Symposium on Languages, Applications and Technologies (SLATE 2023)pt
degois.publication.titleOpen Access Series in Informatics (OASIcs)pt
dc.relation.publisherversionhttps://drops.dagstuhl.de/entities/document/10.4230/OASIcs.SLATE.2023.1pt
dc.peerreviewedyespt
dc.identifier.doi10.4230/OASIcs.SLATE.2023.1pt
degois.publication.volume113pt
dc.date.embargo2023-10-15*
uc.date.periodoEmbargo0pt
item.openairetypebookPart-
item.fulltextCom Texto completo-
item.languageiso639-1en-
item.grantfulltextopen-
item.cerifentitytypePublications-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
crisitem.author.researchunitCISUC - Centre for Informatics and Systems of the University of Coimbra-
crisitem.author.parentresearchunitFaculty of Sciences and Technology-
crisitem.author.orcid0000-0001-6923-900X-
Appears in Collections:FCTUC Eng.Informática - Livros e Capítulos de Livros
Files in This Item:
File Description SizeFormat
OASIcs.SLATE.2023.1.pdf1.63 MBAdobe PDFView/Open
Show simple item record

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.