Knowledge Graph Embedding via Dynamic Mapping Matrix
Встраивание (эмбеддинг) графа знаний с помощью динамической матрицы отображения
2015-01-01
SCID: 54.1/rvfcdue5
Discuss with AI
Dynamic Mapping MatrixKnowledge Base CompletionKnowledge Graph EmbeddingKnowledge RepresentationTranslational Embedding
Figures from the paper
Abstract (AI)
Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.
Key Findings
1
Demonstrates that modeling relation-specific transformations with a mapping matrix captures diverse relation types better than static methods.
2
Introduces dynamic (relation-specific) mapping that projects entity embeddings into relation space for improved representation.
3
Proposes a knowledge graph embedding model that uses a dynamic mapping matrix to represent relations.
4
Shows empirical improvements over baseline embedding approaches on standard knowledge graph tasks (link prediction/knowledge completion).
Research Object
Knowledge graph embedding model using a dynamic mapping matrix
Research Subject
Learning entity and relation embeddings via a dynamic mapping matrix to improve representation and inference in knowledge graphs
Publication Details
Publication Date
2015-01-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest