TY - GEN
T1 - Path-based attention neural model for fine-grained entity typing
AU - Zhang, Denghui
AU - Li, Manling
AU - Cai, Pengshan
AU - Jia, Yantao
AU - Wang, Yuanzhuo
N1 - Publisher Copyright:
Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2018
Y1 - 2018
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85060455544&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060455544&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85060455544
T3 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
SP - 8179
EP - 8180
BT - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
T2 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
Y2 - 2 February 2018 through 7 February 2018
ER -