SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions

Authors

  • Han Xiao Tsinghua University
  • Minlie Huang Tsinghua University
  • Lian Meng Tsinghua University
  • Xiaoyan Zhu Tsinghua University

DOI:

https://doi.org/10.1609/aaai.v31i1.10952

Keywords:

Knowledge Graph, Representation Learning, Semantic Analysis, Textual Information

Abstract

Knowledge graph embedding represents entities and relations in knowledge graph as low-dimensional, continuous vectors, and thus enables knowledge graph compatible with machine learning models. Though there have been a variety of models for knowledge graph embedding, most methods merely concentrate on the fact triples, while supplementary textual descriptions of entities and relations have not been fully employed. To this end, this paper proposes the semantic space projection (SSP) model which jointly learns from the symbolic triples and textual descriptions. Our model builds interaction between the two information sources, and employs textual descriptions to discover semantic relevance and offer precise semantic embedding. Extensive experiments show that our method achieves substantial improvements against baselines on the tasks of knowledge graph completion and entity classification.

Downloads

Published

2017-02-12

How to Cite

Xiao, H., Huang, M., Meng, L., & Zhu, X. (2017). SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.10952

Issue

Section

Main Track: NLP and Knowledge Representation