Research on the Entity Relation Extraction of Field Based on Semi-Supervised

Abstract:

Aim at the problem of supervised learning needing much labeled data for training, this paper proposes a new method based on Semi-Supervised learning. Firstly, to construct a classifier of certain accuracy, small-scale training data was used.Secondly, with the self-expanding idea, we applied the method of information entropy to select some new instances of higher credibility from candidate instances, which were to be predicted by the classifier. Finally, with the expansion of training data, training classifier re-iteratively, classification performance tended to be stable iteration termination, which achieved the entity relation extraction of tourism field by semi-supervised learning. The experiments result show that the new classifier which applies information entropy to iteratively expand training data to be trained makes the precision rate increase by 7% and the F-score increase by 15%.

• Periodical: Advanced Materials Research (Volumes 225-226)
• Pages: 1292-1300
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.225-226.1292
• Online since: April 2011
• Authors: Jian Yi Guo, Jun Zhao, Zheng Tao Yu, Lei Su, Yan Tuan Xian, Wei Tian
• Keywords: Bootstrapping, Credibility, Maximum Entropy Classifier, Semi-Supervised, Unlabeled

References

[1] Automatic Content Extraction 2008 Evlaluation Plan (ACE 08) [EB/OL](2008). http://www.nist.gov.speech/tests/ace/2008/doc/ace08-evalplan.v1.2.pdf.

[2] Zhou G.D., Su J.,Zhang J.,Zhang M..Exploring Various Knowledge in Relation Extraction[c]//Proc of 43rd Annua1 Meeting of the Association for Computational Linguistics, University of Michigan,USA,(2005)p,427-434

[3] Che W X., Liu T., Li S. Automatic Entity Relation Extraction [J]. Journal of Chinese Information Processing, Vol.19(2005),p,1-6.

[4] Dong J.,Sun L.,Feng Y Y.. Chinese Automatic Entity Relation Extraction [J].Journal of Chinese Information Processing, Vol.21(2007),p,80-85.

[5] Zhang Y H., Guo J Y., Yu Z T.,etc.Automatic Entity Relation Extraction for the Field of Tourism[J].Journal of Computational Information Systems,Vol.5(2009),p,1653-1659.

[6] Jiang J F., Wang S X. A Bootstrapping Method for Acquisition of Bi-relations and Bi-relational Patterns [J]. Journal of Chinese Information Processing, Vol.19(2004),p,71-77.

[7] He T T.,Xu C.,etc.Name Entity Relation Extraction Method Based on Seed Self-expansion[J].Computer Engineering,Vol.21(2006),p,183-184.

[8] Zhang Z.Weakly-supervised relation classification for Information Extraction.In Proceedings of ACM the 13th conference on Information and Knowledge Management (CIKM'2004).Washington D.C.USA: ACM press,(2004),p,581-588.

DOI: 10.1145/1031171.1031279

[9] Xi B., Zhou G D., Qian LH.,Pan K..Weakly-Supervised Semantic Relation Extraction Using Stratified Strategy[J]. Journal of Guangxi Normal University(Natural Science Edition),Vol.26(2008),p,178-181.

[10] A.L. Berger V.J. Della Pietra S.A. Della Pietra.A maximum Entropy Approach to Natural Language Processing[J].Computational Linguistics,Vol.22(1996),p,39-71. 显示对应的拉丁字符的拼音