Observatorio de I+D+i UPM

Memorias de investigación
Communications at congresses:
NLP4Types: Predicting Types Using NLP
Year:2018
Research Areas
  • Information technology and adata processing
Information
Abstract
Type inference for resources in Knowledge Graphs is a widely studied problem, for which di erent approaches have been proposed, in- cluding reasoning, statistical analysis, and the usage of the textual in- formation related to the resources. We focus on the latter, exploiting text classi?cation techniques for predicting semantic types from textual descriptions. In this paper we introduce NLP4Types, an online tool that combines di erent standard NLP techniques and classi?ers for predict types based on DBpedia abstracts, as well as to collect feedback from the users for those predictions.
International
Si
Congress
21st International Conference on Knowledge Engineering and Knowledge Management EKAW 2018
960
Place
Nancy, Francia
Reviewers
Si
ISBN/ISSN
1613-0073
Start Date
12/11/2018
End Date
16/11/2018
From page
57
To page
60
EKAW-PD 2018 Proceedings of the EKAW 2018 Posters and Demonstrations Session co-located with 21st International Conference on Knowledge Engineering and Knowledge Management (EKAW 2018)
Participants
  • Autor: Idafen Santana Perez (UPM)
  • Autor: Mariano Rico Almodovar (UPM)
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Ontology Engineering Group
  • Departamento: Inteligencia Artificial
S2i 2020 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)