On Completing Sparse Knowledge Base with Transitive Relation Embedding

Zili Zhou, Shaowu Liu, Guandong Xu, Wu Zhang

AAAI 2019 pp. 3125-3132

doi:10.1609/AAAI.V33I01.33013125 /aaai/2019/zhou2019aaai-completing/

Abstract

Multi-relation embedding is a popular approach to knowledge base completion that learns embedding representations of entities and relations to compute the plausibility of missing triplet. The effectiveness of embedding approach depends on the sparsity of KB and falls for infrequent entities that only appeared a few times. This paper addresses this issue by proposing a new model exploiting the entity-independent transitive relation patterns, namely Transitive Relation Embedding (TRE). The TRE model alleviates the sparsity problem for predicting on infrequent entities while enjoys the generalisation power of embedding. Experiments on three public datasets against seven baselines showed the merits of TRE in terms of knowledge base completion accuracy as well as computational complexity.

PDF AAAI Semantic Scholar

Cite

Text

Zhou et al. "On Completing Sparse Knowledge Base with Transitive Relation Embedding." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33013125

Markdown

[Zhou et al. "On Completing Sparse Knowledge Base with Transitive Relation Embedding." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/zhou2019aaai-completing/) doi:10.1609/AAAI.V33I01.33013125

BibTeX

@inproceedings{zhou2019aaai-completing,
  title     = {{On Completing Sparse Knowledge Base with Transitive Relation Embedding}},
  author    = {Zhou, Zili and Liu, Shaowu and Xu, Guandong and Zhang, Wu},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {3125-3132},
  doi       = {10.1609/AAAI.V33I01.33013125},
  url       = {https://mlanthology.org/aaai/2019/zhou2019aaai-completing/}
}