Share Email Print

Proceedings Paper

Progress toward a statistical model of Chinese POI abbreviation
Author(s): Sen Xu; Xuehu Zhang; Shujie Mao; Haoming Ma; Qi Li
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

POI abbreviation matching is one difficult aspect of POI name matching, since Chinese POI abbreviations have Eastern Language specialty and are mostly formed without strict rules. Examinations of existed website that contains POI name matching are made and approaches proposed are analyzed. To catch the special regularities of POI abbreviation, a statistical model consists mainly of Markov Chain is built to simulate the process of POI abbreviation forming. Detailed algorithm, corpus-building instructions and test results was presented in this paper. A future improving direction was also presented as a result of error analyses.

Paper Details

Date Published: 10 August 2007
PDF: 9 pages
Proc. SPIE 6753, Geoinformatics 2007: Geospatial Information Science, 67530Y (10 August 2007); doi: 10.1117/12.761745
Show Author Affiliations
Sen Xu, Peking Univ. (China)
Xuehu Zhang, Peking Univ. (China)
Shujie Mao, Peking Univ. (China)
Haoming Ma, Peking Univ. (China)
Qi Li, Peking Univ. (China)

Published in SPIE Proceedings Vol. 6753:
Geoinformatics 2007: Geospatial Information Science
Jingming Chen; Yingxia Pu, Editor(s)

© SPIE. Terms of Use
Back to Top