Developing a statistical formula for identifying four-character words in chinese text.

• Main Author: Chua, Hiang Ngee.
• Other Authors: Wee Kim Wee School of Communication and Information
• Format: Theses and Dissertations
• Published: 2008
• Subjects: DRNTU::Library and information science::Libraries::Technologies
• Online Access: http://hdl.handle.net/10356/2108
• Institution: Nanyang Technological University

3 new statistical formulas were developed for identifying 4-character words in Chinese text. These formulas were constructed by performing stepwise logistic regression using the same set of data created Dai, Khoo & Loh (1999).