Abstract
Knowledge bases are useful resources for many natural language processing tasks, however, they are far from complete. In this paper, we define a novel entity representation as a mixture of its neighborhood in the knowledge base and apply this technique on TransE—a well-known embedding model for knowledge base completion. Experimental results show that the neighborhood information significantly helps to improve the results of the TransE, leading to better performance than obtained by other state-of-the-art embedding models on three benchmark datasets for triple classification, entity prediction and relation prediction tasks.
Original language | English |
---|---|
Title of host publication | CoNLL 2016 - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) - Proceedings of the Conference |
Editors | Yoav Goldberg, Stefan Riezler |
Place of Publication | Stroudsburg PA USA |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 40-50 |
Number of pages | 11 |
ISBN (Electronic) | 9781945626197 |
DOIs | |
Publication status | Published - 2016 |
Externally published | Yes |
Event | Conference on Natural Language Learning 2016 - Berlin, Germany Duration: 11 Aug 2016 → 12 Aug 2016 Conference number: 20th https://www.conll.org/2016 https://www.aclweb.org/anthology/volumes/K16-1/ (Proceedings) |
Conference
Conference | Conference on Natural Language Learning 2016 |
---|---|
Abbreviated title | CoNLL 2016 |
Country/Territory | Germany |
City | Berlin |
Period | 11/08/16 → 12/08/16 |
Internet address |
Keywords
- Embedding model
- Entity prediction
- Knowledge base completion
- Link prediction
- Mixture model
- Relation prediction
- Triple classification