Path-Based Attention Neural Model for Fine-Grained Entity Typing
Denghui Zhang, Manling Li, Pengshan Cai, Yantao Jia, Yuanzhuo Wang · Proceedings of the AAAI Conference on Artificial Intelligence · 2018
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.