Research on Chinese Named Entity Recognition Based on Ontology

Abstract:

As a critical role in many Natural Language Processing (NLP) applications, such as Information Extraction, Machine Translation etc, Chinese Named Entity Recognition (NER) remains a challenging task because of its characteristics. This paper proposes a method of Chinese NER, which combining Conditional Random Fields (CRFs) model with domain ontology as a semantic feature besides word and part of speech features. Experiments were made to compare the two kinds of feature templates, and the precision rate and recall rate of Chinese NER rose to 90.86% and 88.23%, which showed remarkable performance of the proposed approach. Combination of ontology and CRFs method increased effectively the precision and recall of Chinese NER.

• Periodical: Applied Mechanics and Materials (Volumes 195-196)
• Pages: 1180-1185
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.195-196.1180
• Online since: August 2012
• Authors: Wei Li Chang, Fang Luo, Ji Lai Qian
• Keywords: CRFs, Domain Ontology, Feature Selection, NER

References

[1] Wenliang Chen, Yujie Zhang, and Hitoshi Isahara. 2006. Chinese Named Entity Recogniton with Conditional Random Fields. In SIGHAN-5, pages 118-121, Sydney, Australia, July22-23.

[2] Burr Settles. Biomedical Named Entity Recognition Using Conditional Random Fields and Rich Feature Sets. COLING, (2004).

DOI: 10.3115/1567594.1567618

[3] Shaojun Zhao. Named Entity Recognition in Bilmedical Texts using an HMM Model. JNLPB, (2004).

[4] Hai Leong Chieu, Hwee Tou NG. Named Entity Recognition: A Maximum Entropy Approach Using Global Information. COLING, Taipei, Taiwan, (2002).

DOI: 10.3115/1072228.1072253

[5] BERNERS-LEE T，HENDLER J，LASSILA O. The Semantic Web[J]. Scientific American, 2001，284(5)：34-43.

DOI: 10.1038/scientificamerican0501-34

[6] Hanna M. Wallach, Conditional Random Fields: An Introduction. Technical Report MS-CIS-04-21. Department of Computer and Information Sciende, University of PENNSylvania, (2004).

[7] Lafferty J, McCallum A, Pereira F. Conditional random fiels: Probabilistic models for segmenting and labeling sequence data[C]. /Broadley C, Danyluk A, eds. Proc. of the 18th Int'1 Conf. on Machine Learning (ICML-01). Williams College: Morgan Kaufmann Publishers, 2001: 282-289.

DOI: 10.1145/1015330.1015422

[8] Dongjian Liao, Dayuan Cao, Xinying Li. Information Extraction Based on Ontology[J]. Computer Enginnering and Applications, 2002(5)：8-15.

[9] Xianyi Cheng, Qian Zhu, Jin Wang. Chinese Information Extraction Principle and Apllication[M]（in chinese）. Beijing Science Publishing House, 2010: 151-182.

[10] Guanming Zeng. CRFs-based Chinese Named Enitity Recognition with Improved Tag Set[D]. Beijing: Beijing University of Posts and Telecommunications, (2009).

DOI: 10.1109/csie.2009.551

[11] Gloria L Zuniga. Ontology: Its Transformation form Philosophy to Informationn Systems[C]. Proceedings of the International Conference on Formal Ontology in Information Systems, 2001: 187-197.

DOI: 10.1145/505168.505187

[12] Sumin Shi. Chinese Coreference Resoulution and Related Technical Research Based on Domain Ontology[D], NanJing: Nanjing University of Science and Technology, (2008).

[13] Mei Wang. Research of The Constructing Methods on OWL Ontology[J]. Library and Information Service, 2006, (12): 30-33.

[14] Jing Ma, Qingqing Song, Sifeng liu. The Comprehensive Construction and Evolution of Domain Ontology[J]. Journal of the China Society for Scientific and Technical Information, 2007, 26(6): 827-832.

DOI: 10.1109/gsis.2007.4443395

[15] Hai Zhao, Chunyu Kit. Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition. The Sixth SIGHAN Workshop on Chinese Language Processing(SIGHAN-6), pp.106-111, Hyderabad, India, Januarey 11-12, (2008).

DOI: 10.1109/icmlc.2009.5212769

[16] Guangjing Jin, Xiao Chen. The Fourth International Chinese Language Processing Bakeoff: Chinese Word Segmentation, Named Entity Recognition and Chinese POS Tagging . The Sixth SIGHAN Workshop on Chinese Language Procdssing. pp.69-81.

DOI: 10.3115/1119250.1119276

[17] The Sogou Lab. http: /www. sogou. com/labs.