Abstract
This paper introduces a method of constructing a semantic dependency knowledge graph (SDKG) by using the rich semantic knowledge in HowNet. The establishment of SDKG depends on correspondence between the lexical dependency labels in semantic dependence bank of BLCU-HIT and the event roles in HowNet. For words with few event roles or those which are not included in the knowledge graph, sememes are recommended to them based on SPWE and SPASE algorithms to extend the SDKG. The paper demonstrates that the experiments achieve an accuracy of 86% when the sememe recommendation is conducted. Considering the establishment of the dependency relationship, a correspondence table in this paper including 87 pieces of data of event role labels mapping to dependency labels is designed. The constructed SDKG has nearly 500000 nodes that contains rich dependency information, which can be used to assist the analysis of the Semantic Dependency Parser. Besides, the results of Semantic Dependency Analysis can be drawn on to supplement the SDKG.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Shao, Y., Qiu, L., Liang, C., Mao, N.: Construction and analysis technology of Chinese semantic dependency TreeBank. In: Sun, M., Chen, Q. (eds.) The 11th Chinese National Conference on Computational Linguistics, Advances of Computational Linguistics in China, pp. 236–241. Tsinghua University Press, Luoyang (2011). (in Chinese)
Liu, Q., Li, Y., Duan, H., Liu, Y., Qin, Z.: Knowledge graph construction techniques. J. Comput. Res. Dev. 53(3), 582–600 (2016). (in Chinese)
Xu, Z., Sheng, Y., He, L., Wang, Y.: Review on knowledge graph techniques. J. Univ. Electron. Sci. Technol. China 45(04), 589–606 (2016). (in Chinese)
HowNet. http://www.keenage.com. Accessed 14 May 2019
Neo4j. https://neo4j.com. Accessed 14 May 2019
Zhu, J., Yang, Y., Xu, B., Li, J.: Semantic representation learning based on HowNet. J. Chin. Inf. Process. 33(3), 33–41 (2019). (in Chinese)
Sun, M., Chen, X.: Embedding for words and word senses based on human annotated knowledge base: a case study on HowNet. J. Chin. Inf. Process. 30(6), 1–6 (2016)
Niu, Y., Xie, R., Liu, Z., Sun, M.: Improved word representation learning with sememes. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, vol. 1 (Long Papers), pp. 2049–2058. Association for Computational Linguistics, Vancouver (2017)
Xie, R., Yuan, X., Liu, Z., Sun, M.: Lexical sememe prediction via word embeddings and matrix factorization. In: IJCAI 2017 Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 4200–4206. AAAI Press, Melbourne (2017)
Acknowledgments
This research project is supported by the National Natural Science Foundation of China (61872402), the Humanities and Social Science Project of the Ministry of Education (17YJAZH068), Science Foundation of Beijing Language and Culture University (supported by “the Fundamental Research Funds for the Central Universities”) (18ZDJ03), the Fundamental Research Funds for the Central Universities and the Research Funds of Beijing Language and Culture University (19YCX122). In this way, we are sincerely grateful for the foundations.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, S., Li, Y., Shao, Y., Wang, L. (2020). Building Semantic Dependency Knowledge Graph Based on HowNet. In: Hong, JF., Zhang, Y., Liu, P. (eds) Chinese Lexical Semantics. CLSW 2019. Lecture Notes in Computer Science(), vol 11831. Springer, Cham. https://doi.org/10.1007/978-3-030-38189-9_54
Download citation
DOI: https://doi.org/10.1007/978-3-030-38189-9_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-38188-2
Online ISBN: 978-3-030-38189-9
eBook Packages: Computer ScienceComputer Science (R0)