Abstract
A unified platform to extract all kinds of vocabulary should be required for vocabulary monitoring. We argue just like other physical movements all words are doing the temporal-spatial movement. The classification of vocabulary is actually based on the types of movement. To model the temporal-spatial movement will lead to the extraction of all kinds of words. Therefore this paper proposes the temporal-spatial model of vocabulary movement with three quantities that is the state function, the state change function and the speed function. Furthermore the two new metrics (the normalized usage and the usage ratio) are proposed to calculate the model quantities. The model has been applied to extract the catchwords, new words, terminologies, commonly used words, and emergency terms. The results show that the temporal-spatial model has good robustness, which can eliminate the influence of the different corpus scale and give a package solution for vocabulary monitoring.
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
Preview
Unable to display preview. Download preview PDF.
References
Chinese Language Situation in 2011, 1st edn. Department of Language Information Management in the Ministry of Education. The Commercial Press, Beijing (2011)
Zhang, H.J., Shi, S.M., Zhu, Z.Y., Huang, H.Y.: Summarize of Chinese New Words Recognition Technology. Computer Science 3, 6–16 (2010)
Wu, Y., Yan, P.J., Di, L.F.: New Words Detection Based on a Background Bigram Model. J. Tsinghua University 9, 1317–1320 (2011)
He, W., Hou, M., Wen, C.J.: The Temporal-Spatial Model for Catchwords Monitoring. In: Sun, M.S., Chen, Q.X. (eds.) Frontiers of Content Computing: Research and Application, pp. 276–282. Tsinghua University Press, Beijing (2007)
Zhang, P.: Study on the Dynamic Tracking and Auxiliary Finding of Catchwords Based on DCC. In: Sun, M.S., Chen, Q.X. (eds.) Computing Language and Content-Based Text Processing, pp. 20–28. Tsinghua University Press, Beijing (2003)
You, H.L., Zhang, W., Liu, T.: An Automatic Terms Identification Method Based on the Weighted Voting. Chinese Information Technology 3, 9–16 (2011)
Xun, E.D., Li, S.: The Method of New Terms and Definitions Identification by Using the Definitions Mode of the Terms and Multi-characteristics. Computer Research and Development 1, 62–69 (2009)
Hou, M.: Research on Language Monitoring and Vocabulary Quantification. In: Cao, Y.Q., Sun, M.S. (eds.) Recent Progress in Chinese Information Processing, pp. 76–83. Tsinghua University Press, Beijing (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
He, W., Zhang, J., Zou, Y., Teng, Y., Hou, M. (2013). The Unified Platform for Language Monitoring Based on the Temporal-Spatial Model of Vocabulary Movement. In: Ji, D., Xiao, G. (eds) Chinese Lexical Semantics. CLSW 2012. Lecture Notes in Computer Science(), vol 7717. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-36337-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-36337-5_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-36336-8
Online ISBN: 978-3-642-36337-5
eBook Packages: Computer ScienceComputer Science (R0)