TU Darmstadt / ULB / TUbiblio

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

Mousselly-Sergieh, Hatem and Gurevych, Iryna and Roth, Stefan (2017):
Neural, Multimodal, Energy-based Approach for Knowledge Graph Completion.
In: Language-Learning-Logic Workshop (3L 2017), London, UK, [Conference or Workshop Item]

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.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Mousselly-Sergieh, Hatem and Gurevych, Iryna and Roth, Stefan
Title: Neural, Multimodal, Energy-based Approach for Knowledge Graph Completion
Language: English
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.

Title of Book: Language-Learning-Logic Workshop (3L 2017)
Uncontrolled Keywords: CEDIFOR
Divisions: 20 Department of Computer Science > Ubiquitous Knowledge Processing
20 Department of Computer Science
Event Location: London, UK
Date Deposited: 12 Sep 2017 16:36
Identification Number: TUD-CS-2017-0244
Related URLs:
Export:

Optionen (nur für Redakteure)

View Item View Item