Please use this identifier to cite or link to this item:
https://hdl.handle.net/10316/115592
Title: | Question Answering over Linked Data with GPT-3 | Authors: | Faria, Bruno Perdigão, Dylan Oliveira, Hugo Gonçalo |
Keywords: | SPARQL Generation; Prompt Engineering; Few-Shot Learning; Question Answering; GPT-3 | Issue Date: | 15-Oct-2023 | Publisher: | Schloss Dagstuhl – Leibniz-Zentrum für Informatik | Project: | C645008882-00000055 | metadata.degois.publication.title: | Open Access Series in Informatics (OASIcs) | metadata.degois.publication.volume: | 113 | metadata.degois.publication.location: | 12th Symposium on Languages, Applications and Technologies (SLATE 2023) | Abstract: | This 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. | URI: | https://hdl.handle.net/10316/115592 | DOI: | 10.4230/OASIcs.SLATE.2023.1 | Rights: | openAccess |
Appears in Collections: | FCTUC Eng.Informática - Livros e Capítulos de Livros |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
OASIcs.SLATE.2023.1.pdf | 1.63 MB | Adobe PDF | View/Open |
Page view(s)
48
checked on Oct 30, 2024
Download(s)
14
checked on Oct 30, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.