Title: Chinese entity attributes extraction based on bidirectional LSTM networks

Authors: Zhonghe He; Zhongcheng Zhou; Liang Gan; Jiuming Huang; Yan Zeng

Addresses: Department of Computer, National University of Defense Technology, Changsha, Hunan, 410073, China ' Department of Computer, National University of Defense Technology, Changsha, Hunan, 410073, China ' Department of Computer, National University of Defense Technology, Changsha, Hunan, 410073, China ' Department of Computer, National University of Defense Technology, Changsha, Hunan, 410073, China ' Hunan Xinghan Data and AI Technology Co., Ltd., No. 649 North Station Road, Kaifu District, Changsha, Hunan, 410003, China

Abstract: For the low performance of slot filling method applied in Chinese entity - attribute extraction at present, this paper presents a distant supervision relation extraction method based on bidirectional long short-term memory neural network. First we get the Infobox of Baidu baike, using relation triples of Infobox to get the training corpus from the internet and then we train the classifier based on bidirectional LSTM Networks. Compared with classical methods, the method of this paper is fully automatic in the aspect of data annotation and feature extraction. Experiment results show that the proposed method is effective and it is suitable for information extraction in high dimensional space. Compared with the SVM algorithm, the accuracy rate is significantly improved.

Keywords: long short-term memory; LSTM; information extraction; deep learning; entity relation extraction; ERE.

DOI: 10.1504/IJCSE.2019.10017884

International Journal of Computational Science and Engineering, 2019 Vol.18 No.1, pp.65 - 71

Received: 10 Mar 2017
Accepted: 27 Sep 2017

Published online: 14 Dec 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article