A Novel Multimodal Deep Neural Network Framework for Extending Knowledge Base
Document title: A Novel Multimodal Deep Neural Network Framework for Extending Knowledge Base
Journal: Computación y sistemas
Database: PERIÓDICA
System number: 000411064
ISSN: 1405-5546
Authors: 1
1
2
1
Institutions: 1Beijing University of Posts and Telecommunications, Beijing. China
2Universite Pierre et Marie Curie, París. Francia
Year:
Season: Jul-Sep
Volumen: 20
Number: 3
Pages: 459-466
Country: México
Language: Inglés
Document type: Artículo
Approach: Experimental, aplicado
English 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
Disciplines: Ciencias de la computación,
Literatura y lingüística
Keyword: Procesamiento de datos,
Lingüística aplicada,
Lingüística computacional,
Inserción de palabras,
Bases de conocimiento,
Redes neuronales
Keyword: Computer science,
Literature and linguistics,
Data processing,
Applied linguistics,
Computing linguistics,
Word embedding,
Knowledge bases,
Neural networks
Full text: Texto completo (Ver HTML)