Path-Based Attention Neural Model for Fine-Grained Entity Typing

Authors

  • Denghui Zhang Institute of Computing Technology, Chinese Academy of Sciences
  • Manling Li Institute of Computing Technology, Chinese Academy of Sciences
  • Pengshan Cai University of Massachusetts Amherst
  • Yantao Jia Institute of Computing Technology, Chinese Academy of Sciences
  • Yuanzhuo Wang Institute of Computing Technology, Chinese Academy of Sciences

Keywords:

Fine-Grained Entity Typing

Abstract

Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure. It suffers from the label noise in training data generated by distant supervision. Although recent studies use many features to prune wrong label ahead of training, they suffer from error propagation and bring much complexity. In this paper, we propose an end-to-end typing model, called the path-based attention neural model (PAN), to learn a noise-robust performance by leveraging the hierarchical structure of types. Experiments on two data sets demonstrate its effectiveness.

Downloads

Published

2018-04-29

How to Cite

Zhang, D., Li, M., Cai, P., Jia, Y., & Wang, Y. (2018). Path-Based Attention Neural Model for Fine-Grained Entity Typing. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12162