Comprehensive Information Based Methodology forNatural Language Understanding

JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM ›› 2004, Vol. 27 ›› Issue (4): 1-12.

Comprehensive Information Based Methodology for
Natural Language Understanding

ZHONG Yi-xin

Center of Intelligence Science and Technology Research, Beijing University of Posts and
Telecommunications, Beijing 100876, China

Received:2003-04-21 Online:2004-04-28

Abstract

Abstract: The “Comprehensive Information Based Methodology forNatural Language Understanding” presented in the paper is an application of the Comprehensive Information(CI) Theory, which was established by the author of the paper years ago formeeting the needs in artificial intelligence research. Different from other works in the field of natural language processing, the major features of the methodology presented in the paper include two folds. Firstly, instead of the syntacticor/and semantic information is used, all components of the comprehensive information are fully utilized for natural language understanding. Secondly, instead of using one or another approach preferably, both the rule-based approach and the statistics-based approach have been complementarily integrated. The successesof the research projects guided by the methodology and completed last few yearsprove the methodology promising.

Key words: natural language understanding, comprehensive information theory, rule-based approach, statistical approach, CI-basedmethodology for natural language understanding

CLC Number:

T P18

ZHONG Yi-xin. Comprehensive Information Based Methodology for
Natural Language Understanding
[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2004, 27(4): 1-12.

References

[1]　Sha nnon C E. A mathematical theor y of communicatio n [J], Bell System Tech J, 1948, 27: 379-423, 623-656.
[2]　钟义信. 信息科学原理[M ]. 第3版.北京: 北京邮电大学出版社, 2002.Zho ng Y X. Principles o f info rma tion science [M ]. Th e third edtio n. Beijing: Beijing Univ er sity of Posts and Telecommunica tio ns Press, 2002.
[3]　Wiener N. Cyber netics [M ]. New Yo rk: Wiley , 1948.
[4]　钟义信. 知行学: 信息-知识-智能的统一理论[J].中国工程科学, 2004, 6( 7): 1-8.Zho ng Y X. A unified th eo r y of info rma tion, know ledg e a nd intellig ence [J ]. China Engineering Science, 2004, 6( 7): 1-8.
[5]　郭祥昊. 基于概念网络的N EWS系统[D].北京: 北京邮电大学信息工程学院, 1999.Guo X H. N EWS-an automatic abstract sy stem [D ]. Beijing: Informatio n Engineering Schoo l, Beijing Univ er sity o f Po sts and Telecommunications, 1999.
[6]　李蕾. 基于全信息的LADIES系统[D]. 北京: 北京邮电大学信息工程学院, 2000.Li L. LADIES-CI-based summariza tio n sy stem [D]. Beijing: Info rmation Engineering Schoo l, Beijing Univ er sity o f Po sts and Telecommunications, 2000.
[7]　刘伟权. 基于规则与统计相结合的GLANN CE系统[D]. 北京: 北京邮电大学信息工程学院, 1998.Liu W Q. GLANNCE-an abstract sy stem based on the combina tio n o f rule and sta tistics [D]. Beijing:Info rma tio n Engineering Scho ol, Beijing Univ er sity o f Po sts a nd Telecommunications, 1998.
[8]　胡舜耕. 多智能体的理论研究与实现[D]. 北京: 北京邮电大学信息工程学院, 2001.Hu S G. Multi-ag ent: theo retical resear ch and implementation [D]. Beijing: Info rmation Engineering Schoo l, Beijing Univ ersity o f Posts and Telecommunica tio ns, 2001.
[9]　落红卫. 智能防火墙的研究与开发[D]. 北京: 北京邮电大学信息工程学院, 2003. Luo H W. An R& D in int ellig ent firew all [D ]. Beijing: Info rma tion Enginee ring Scho ol, Beijing Univ er sity o f Po sts and Telecommunications, 2003.