Previous [ 1] [ 2] [ 3] [ 4] [ 5] [ 6] [ 7] [ 8] [ 9] [ 10] [ 11] [ 12]

@

Journal of Information Science and Engineering, Vol. 21 No. 1, pp. 223-233 (January 2005)

A Non-Training Approach to Generating High Semantic
Titles for Chinese Documents

Gai-Tai Huang and Hsiu-Hsen Yao*
The Institute of Strategic Defense Management
National Defense Management College, NDU
Taipei, 235 Taiwan
E-mail: hgt@rs590.ndmc.edu.tw
*Department of Computer Engineering
Yuan Ze University
Taoyuan, 320 Taiwan
E-mail: csyao@saturn.yzu.edu.tw

Due to the abundance of available data, manual title generation may become unfeasible. Traditionally, information retrieval has been applied to perform automatic title generation by exploring and searching for keywords from a document. However, titles generated through such a direct combination approach may not satisfy Chinese grammatical rules, and also may not express the semantic meaning explicitly. Thus, we propose a non-learning approach based on conceptual schema to generating titles automatically through sentence modification and recombination. Experimental results prove that our model can satisfy the automatic title generation requirements.

Keywords: relation model, conceptual schema, title generation, information retrieval, Chinese document

Full Text () Retrieve PDF document (200501_12.pdf)

Received August 9, 2002; revised July 7 and November 28, 2003; accepted February 2, 2004.
Communicated by Kuo-Chin Fan.