Jointly embedding relations and mentions for knowledge population

Miao Fan, Kai Cao, Yifan He, Ralph Grishman

Research output: Contribution to journalConference articlepeer-review


This paper contributes a joint embedding model for predicting relations between a pair of entities in the scenario of relation inference. It differs from most standalone approaches which separately operate on either knowledge bases or free texts. The proposed model simultaneously learns low-dimensional vector representations for both triplets in knowledge repositories and the mentions of relations in free texts, so that we can leverage the evidence both resources to make more accurate predictions. We use NELL to evaluate the performance of our approach, compared with cutting-edge methods. Results of extensive experiments show that our model achieves significant improvement on relation extraction.

Original languageEnglish (US)
Pages (from-to)186-191
Number of pages6
JournalInternational Conference Recent Advances in Natural Language Processing, RANLP
StatePublished - 2015
Event10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015 - Hissar, Bulgaria
Duration: Sep 7 2015Sep 9 2015

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Artificial Intelligence
  • Electrical and Electronic Engineering


Dive into the research topics of 'Jointly embedding relations and mentions for knowledge population'. Together they form a unique fingerprint.

Cite this