A Novel Multimodal Deep Neural Network Framework for Extending Knowledge Base

Yu Zhao 1 Sheng Gao 2 Patrick Gallinari 2 Jun Guo 3
1 LAAS-OSE - Équipe Optoélectronique pour les Systèmes Embarqués
LAAS - Laboratoire d'analyse et d'architecture des systèmes [Toulouse]
2 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : Knowledge base is a very important database for knowledge management, which is very useful for Question Answering, Query Expansion and other AI tasks. However, due to the fast-growing knowledge on the web and not all common knowledge expressed in the text is explicit, the knowledge base always suffers from incompleteness. Recently many researchers are trying to solve the problem as link prediction, only using the existing knowledge base, however, it is just knowledge base completion without adding new entities, which emerges from unstructured text not in existing knowledge base. In this paper, we propose a multimodal deep neural network framework that trying to learn new entities from unstructured text and to extend the knowledge base. Experiments demonstrate the excellent performance.
Document type :
Journal articles
Complete list of metadatas

Contributor : Patrick Gallinari <>
Submitted on : Thursday, May 18, 2017 - 5:22:48 PM
Last modification on : Tuesday, May 14, 2019 - 11:01:04 AM


  • HAL Id : hal-01524735, version 1


Yu Zhao, Sheng Gao, Patrick Gallinari, Jun Guo. A Novel Multimodal Deep Neural Network Framework for Extending Knowledge Base. Computación y Sistemas, 2016, 20 (3), pp.459-466. ⟨hal-01524735⟩



Record views