Title: Using deep belief networks to extract Chinese entity attribute relation in domain-specific

Authors: Yantuan Xian; Fa Shao; Jianyi Guo; Lanjiang Zhou; Zhengtao Yu; Wei Chen

Addresses: School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China; Key Laboratory of Pattern Recognition and Intelligent Computing of Yunnan College, Kunming, Yunnan, China ' School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China ' School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China; Key Laboratory of Pattern Recognition and Intelligent Computing of Yunnan College, Kunming, Yunnan, China ' School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China; Key Laboratory of Pattern Recognition and Intelligent Computing of Yunnan College, Kunming, Yunnan, China ' School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China; Key Laboratory of Pattern Recognition and Intelligent Computing of Yunnan College, Kunming, Yunnan, China ' School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China; Key Laboratory of Pattern Recognition and Intelligent Computing of Yunnan College, Kunming, Yunnan, China

Abstract: The state-of-the-art methods used for entity attribute relation extraction are primarily based on statistical machine learning, and the performance strongly depends on the quality of the extracted features. Deep belief networks (DBN) has been successful in the high dimensional feature space information extraction task, which can without complicated pre-processing. In this paper, the DBN, which consists of one or more restricted Boltzmann machine (RBM) layers and a back-propagation (BP) layer, is presented to extract Chinese entity attribute relation in domain-specific. First, the word tokens are transformed to vectors by looking up word embeddings. Then, the RBM layers maintain as much information as possible when feature vectors are transferred to next layer. Finally, the BP layer is trained to classify the features generated by the last RBM layer, and adopting Levenberg-Marquard (LM) optimisation algorithm to do the training. The experimental results show that the proposed method outperforms state-of-the-art learning models in specific domain entity attribute relation extraction.

Keywords: domain-specific relation extraction; Chinese entity attributes; deep belief networks; combination features; Levenberg-Marquard; LM optimisation; restricted Boltzmann machine; RBM; backpropagation; entity attribute relations.

DOI: 10.1504/IJCSM.2016.076422

International Journal of Computing Science and Mathematics, 2016 Vol.7 No.2, pp.144 - 155

Received: 22 Jul 2015
Accepted: 25 Aug 2015
Published online: 06 May 2016 *

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