Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure. Traditional distant supervision based methods employ a structured data source as a weak supervision and do not need hand-labeled data, but they neglect the label noise in the automatically labeled training corpus. Although recent studies use many features to prune wrong data 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 demonstrate its effectiveness.
@article{arxiv.1710.10585,
title = {Path-Based Attention Neural Model for Fine-Grained Entity Typing},
author = {Denghui Zhang and Pengshan Cai and Yantao Jia and Manling Li and Yuanzhuo Wang and Xueqi Cheng},
journal= {arXiv preprint arXiv:1710.10585},
year = {2018}
}