Distributed representation learning for knowledge graphs with entity descriptions

Miao Fan, Qiang Zhou, Thomas Fang Zheng, Ralph Grishman

Research output: Contribution to journalArticlepeer-review


Recent studies of knowledge representation attempt to project both entities and relations, which originally compose a high-dimensional and sparse knowledge graph, into a continuous low-dimensional space. One canonical approach TransE [2] which represents entities and relations with vectors (embeddings), achieves leading performances solely with triplets, i.e. (head_entity, relation, tail_entity), in a knowledge base. The cutting-edge method DKRL [23] extends TransE via enhancing the embeddings with entity descriptions by means of deep neural network models. However, DKRL requires extra space to store parameters of inner layers, and relies on more hyperparameters to be tuned. Therefore, we create a single-layer model which requests much fewer parameters. The model measures the probability of each triplet along with corresponding entity descriptions, and learns contextual embeddings of entities, relations and words in descriptions simultaneously, via maximizing the loglikelihood of the observed knowledge. We evaluate our model in the tasks of knowledge graph completion and entity type classification with two benchmark datasets: FB500K and EN15K, respectively. Experimental results demonstrate that the proposed model outperforms both TransE and DKRL, indicating that it is both efficient and effective in learning better distributed representations for knowledge bases.

Original languageEnglish (US)
Pages (from-to)31-37
Number of pages7
JournalPattern Recognition Letters
StatePublished - Jul 1 2017


  • Entity description
  • Entity type classification
  • Knowledge graph
  • Knowledge graph completion
  • Representation learning

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'Distributed representation learning for knowledge graphs with entity descriptions'. Together they form a unique fingerprint.

Cite this