Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling

  • Xu K
  • Feng Y
  • Huang S
 et al. 
  • 115

    Readers

    Mendeley users who have this article in their library.
  • 30

    Citations

    Citations of this article.

Abstract

Syntactic features play an essential role in identifying relationship in a sentence. Previous neural network models often suffer from irrelevant information introduced when subjects and objects are in a long distance. In this paper, we propose to learn more robust relation representations from the shortest dependency path through a convolution neural network. We further propose a straightforward negative sampling strategy to improve the assignment of subjects and objects. Experimental results show that our method outperforms the state-of-the-art methods on the SemEval-2010 Task 8 dataset.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Kun Xu

  • Yansong Feng

  • Songfang Huang

  • Dongyan Zhao

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free