TU Darmstadt / ULB / TUbiblio

Neural, Multimodal, Energy-based Approach for Knowledge Graph Completion

Mousselly-Sergieh, Hatem ; Gurevych, Iryna ; Roth, Stefan (2017)
Neural, Multimodal, Energy-based Approach for Knowledge Graph Completion.
London, UK
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

We propose an approach for knowledge graph (KG) completion that leverages multimodal information on KG entities including: 1) visual features which are obtained using state-of-the-art convolutional neural network models for image classification and 2) textual representations which are learned using word embedding techniques. Our approach builds upon the translation model (Bordes et al., 2013) for KG representation and introduce an energy-based framework that efficiently combines multimodal features. The corresponding KG representations are learned using a simple neural network architecture. We experimentally demonstrate the effectiveness of our approach and compare its performance to other baseline models.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2017
Autor(en): Mousselly-Sergieh, Hatem ; Gurevych, Iryna ; Roth, Stefan
Art des Eintrags: Bibliographie
Titel: Neural, Multimodal, Energy-based Approach for Knowledge Graph Completion
Sprache: Englisch
Publikationsjahr: September 2017
Buchtitel: Language-Learning-Logic Workshop (3L 2017)
Veranstaltungsort: London, UK
Zugehörige Links:
Kurzbeschreibung (Abstract):

We propose an approach for knowledge graph (KG) completion that leverages multimodal information on KG entities including: 1) visual features which are obtained using state-of-the-art convolutional neural network models for image classification and 2) textual representations which are learned using word embedding techniques. Our approach builds upon the translation model (Bordes et al., 2013) for KG representation and introduce an energy-based framework that efficiently combines multimodal features. The corresponding KG representations are learned using a simple neural network architecture. We experimentally demonstrate the effectiveness of our approach and compare its performance to other baseline models.

Freie Schlagworte: CEDIFOR
ID-Nummer: TUD-CS-2017-0244
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung
Hinterlegungsdatum: 12 Sep 2017 16:36
Letzte Änderung: 24 Jan 2020 12:03
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen