Abstract
Entity hyponymy is an important semantic relation to build the domain ontology or knowledge graphs. Traditional extraction methods of domain concepts hyponymy are limited to manual annotation or specific patterns. Aiming at this problem, this paper proposed a new method of extracting hypernym–hyponym relations of domain entity with the CCRFs (Cascaded Conditional Random Fields), i.e., a two-layer CRFs model is employed to learn the hyponymy of domain entity concept. The lower-level of the CCRFs model is used to model the words by considering the dependence of long distance among words and identify the domain entity concept, which need to be combined in order. The pairs of entity concept can be obtained on the basis of the definition template characteristics. Then label the semantic pairs of concepts in high-level model by integrating assemblage characteristics and hyponymy demonstratives in feature template, finally identify the hypernym–hyponym relations between domain entities. Experiments on real-world data sets demonstrate the performance of the proposed algorithms.
Similar content being viewed by others
References
D. M. Yehia, H. A. Hassan, and A. Rafea, “TextOntoEx: Aautomatic ontology construction from natural english text,” Expert Syst. Appl. 34 (2), 1474–1480 (2008).
Liu Kaipeng and Fang Binxing, “Ontology induction based on social annotations,” Jisuanji Xuebao (Chinese J. Comput.) 33 (10), 1823–1834 (2010).
Wang Hui, Zhan Weidong, and Yu Shiwen, “The specification of the semantic knowledge-base of contemporary Chinese,” J. Chinese Language Comput. 13 (2), 159–176 (2003).
J. Pujara, H. Miao, L. Getoor, et al., “Ontology-aware partitioning for knowledge graph identification,” in Proc. 2013 ACM Workshop on Automated Knowledge Base Construction (New York, 2013), pp. 19–24.
Zhao Yu and Li Jianqiang, “Domain ontology learning from websites,” in Proc. 9th IEEE Annu. Int. Symp. on Applications and the Internet SAINT’09 (Bellevue, WA, 2009), pp. 129–132.
Li Lian, et al., “Automated construction Chinese domain ontology from Wikipedia,” in Proc. 4th IEEE Int. Conf. on Natural Computation ICNC’08. (Jinan, Shandong, 2008), Vol. 2, pp. 670–674.
B. Hachey, W. Radford, J. Nothman, et al., “Evaluating entity linking with Wikipedia,” Artificial Intellig. 194, 130–150 (2013).
M. A. Hearst, “Automatic acquisition of hyponyms from large text corpora,” in Proc. 14th Int. Conf. on Computational Linguistics (COLING’92) (Nantes, 1992), Vol. 2, pp. 539–545.
S. A. Caraballo, “Automatic construction of a hypernym-labeled noun hierarchy from text,” in Proc. 37th Annu. Meeting of the Association for Computational Linguistics on Computational Linguistics (Stroudsburg, PA, 1999), pp. 120–126.
P. Cimiano, R. Uwe, and Š. Jasmin, “Ontology-driven discourse analysis for information extraction,” Data Knowledge Eng. 55 (1), 59–83 (2005).
Liu Lei and Cao Cungen. “Hyponymy relation verification method based on hybrid features,” Comput. Eng. 34 (14), 12–13 (2008).
N. Nakaya, M. Kurematsu, and T. Yamaguchi, “A domain ontology development environment using a MRD and text corpus,” Casopís Lékar Ceskych 128 (37), 1166–1169 (2002).
A. Sumida and K. Torisawa, “Hacking Wikipedia for hyponymy relations acquisition,” in Proc. Int. Joint Conf. on Natural Language Processing (Hyderabad, 2008).
N. Garc, A. Renato, S. Schmidt, et al., “Automatic taxonomy extraction in different languages using Wikipedia and minimal language-specific information,” in Proc. Int. Conf. on Computational Linguistics and Intelligent Text Processing (Springer-Verlag, 2012), pp. 42–53.
W. Song, J. Zhou, and W. Qu, “Chinese hyponymy extraction based on dictionary and encyclopedia resources,” J. Data Acquisition Processing 29 (5), 821–827 (2014).
Tian Xiaodan, Wang Qinglin, and Li Yuan, “Hyponymy verification of ontology concepts based on feature vectors,” J. Central South Univ. (Natural Sci. Ed.), No. S2, 351–354 (2013).
Huang Yi, Wang Qinglin, and Liu Yu, “An acquisition method of domain-specific terminological hyponymy based on CRF,” J. Central South Univ. 44 (2), 355–359 (2013).
Q. Zhan and C. Wang, “Hyponymy extraction of domain ontology concept based on CCRFS and hierarchy clustering,” Int. J. Web Semantic Technol. (IJWesT) 6(3) (2015).
J. Lafferty, A. McCallum, et al., “Conditional random fields: Probabilistic models for segmenting and labeling sequence data,” Departmental Papers (CIS) (2001).
Liu Lei, et al., “Sense recognition research of hyponymy based on concept space,” Chinese J. Comput. 32 (8), 1651–1659 (2009).
A. McCallum, “Efficiently inducing features of conditional random fields,” in Proc. 19th Conf. on Uncertainty in Artificial Intelligence (Morgan Kaufmann, San Francisco, CA, 2003), pp. 403–410.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Xiaojun Ma. Born in 1991. Now studying in Kunming University of Science and Technology. Research interest including natural language process, information extraction.
Jianyi Guo. Born in 1964. Professor, ACM and CCF member. Graduated and received Master degree from Xi’an Jiaotong University in 1990. Since 1990, works at Kunming University of Science and Technology. Research interest including pattern recognition, natural language process, information extraction.
Zhengtao Yu. Born in 1970. Professor, ACM and CCF member. Graduated and received Ph.D. from school of computer science, Beijing Institute of Technology in 2005. Dean of school of information engineering and automation in Kunming University of Science and Technology. Research interest including pattern recognition, natural language process, information retrieval.
Cunli Mao. Born in 1977. Received Ph.D from the Kunming University of Science and Technology in 2013. Research interests include pattern recognition, natural language processing, information retrieva.
Yantuan Xian. Born in 1981. PhD candidate at Kunming University of Science and Technology, Kunming, China. Graduated and received his MS degree in Pattern Recognition and Intelligent System from Shenyang Institute of Automation (SIA) of Chinese Academy of Sciences in 2006. His major research interests are pattern recognition and information extraction.
Wei Chen. Born in 1983. Graduated and received his M.S. degree in computer software and theory from school of information of Yunnan University in 2009. His major research interests are information retrieval and information extraction.
Rights and permissions
About this article
Cite this article
Ma, X., Guo, J., Yu, Z. et al. Extracting hyponymy of domain entity using Cascaded Conditional Random Fields. Pattern Recognit. Image Anal. 27, 637–644 (2017). https://doi.org/10.1134/S1054661817030208
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661817030208