English

Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling

Computation and Language 2015-06-26 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.1506.07650,
  title  = {Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling},
  author = {Kun Xu and Yansong Feng and Songfang Huang and Dongyan Zhao},
  journal= {arXiv preprint arXiv:1506.07650},
  year   = {2015}
}
R2 v1 2026-06-22T09:59:58.366Z