Bilinear Joint Learning of Word and Entity Embeddings for Entity Linking

Hui Chen, Baogang Wei, Yonghuai Liu, Yiming Li, Jifang Yu, Wenhao Zhu

Research output: Contribution to journalArticlepeer-review

15 Citations (Scopus)
321 Downloads (Pure)

Abstract

Entity Linking (EL) is the task of resolving mentions to referential entities in a knowledge base, which facilitates applications such as information retrieval, question answering, and knowledge base population. In this paper, we propose a novel embedding method specifically designed for EL. The proposed model jointly learns word and entity embeddings which are located in different distributed spaces, and a bilinear model is introduced to simulate the interaction between words and entities. We treat EL as a ranking problem, and utilize a pairwise learning-to-rank framework with features constructed with learned embeddings as well as conventional EL features. Experimental results show the proposed model produces effective embeddings which improve the performance of our EL algorithm. Our method yields the state-of-the-art performances on two benchmark datasets CoNLL and TAC-KBP 2010
Original languageEnglish
Pages (from-to)12-18
Number of pages7
JournalNeurocomputing
Volume294
Early online date05 Dec 2017
DOIs
Publication statusPublished - 14 Jun 2018

Keywords

  • entity linking
  • embedding model
  • learning to rank
  • entity disambiguation

Fingerprint

Dive into the research topics of 'Bilinear Joint Learning of Word and Entity Embeddings for Entity Linking'. Together they form a unique fingerprint.

Cite this