Title :
Statistical termhood measurement for mono-word terms via corpus comparison
Author :
Liu, Xiao-yue ; Kit, Chunyu
Author_Institution :
Dept. of Chinese, Translation & Linguistics, City Univ. of Hong Kong, Kowloon, China
Abstract :
This paper examines the performance of a number of statistical measures for mono-word termhood within a corpus comparison framework. These measures are defined in terms of the frequency, information, and rank of a term candidate in a domain and a background corpus. The evaluation results from our experiments reveal interesting characteristics of each metric and verify the outstanding performance of those based on enhanced rank and information in identifying true terms.
Keywords :
data mining; information analysis; natural language interfaces; corpus comparison; mono-word terms; statistical termhood measurement; Cybernetics; Data mining; Education; Frequency measurement; Information technology; Knowledge transfer; Machine learning; Natural language processing; Research and development; Terminology; Automatic term recognition; Background corpus; Corpus comparison; Termhood measure;
Conference_Titel :
Machine Learning and Cybernetics, 2009 International Conference on
Conference_Location :
Baoding
Print_ISBN :
978-1-4244-3702-3
Electronic_ISBN :
978-1-4244-3703-0
DOI :
10.1109/ICMLC.2009.5212765
