Very large Bayesian multinets for text classification

被引：4
作者：
Klopotek, MA [1 ]
机构：
[1] Polish Acad Sci, Inst Comp Sci, PL-01237 Warsaw, Poland
来源：
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE | 2005年 / 21卷 / 07期
关键词：
Bayesian; multinets; classification;
D O I：
10.1016/j.future.2004.03.007
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
This paper presents a newly developed algorithm learning very large tree-like Bayesian networks from data and exploits it to create a Bayesian multinet (BMN) classifier for natural language text documents. Results of empirical evaluation of this BMN classifier are presented. The study suggests that tree-like Bayesian networks are able to handle a classification task in 100 000 variables with sufficient speed and accuracy. (c) 2004 Elsevier B.V. All rights reserved.
引用
收藏
页码：1068 / 1082
页数：15
相关论文
共 41 条
[1]  
Aho A. V., 1983, DATA STRUCTURES ALGO
[2]  
Baker L. D., 1998, Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, P96, DOI 10.1145/290941.290970
[3]  
CERQUIDES J, 1999, KNOWLEDGE DISCOVERY, P292
[4]  
CHENG J, LEARNING BAYSIAN BEL
[5]  
Cheng J., 1997, P 6 INT C INF KNOWL
[6]  
CHENG J, 1997, P AI STAT 97 ST LAUD
[7]  
CHICKERING DM, TRANSFORMATIONAL CHA
[8]   APPROXIMATING DISCRETE PROBABILITY DISTRIBUTIONS WITH DEPENDENCE TREES [J].
CHOW, CK ;
LIU, CN .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1968, 14 (03) :462-+
[9]   CONSISTENCY OF AN ESTIMATE OF TREE-DEPENDENT PROBABILITY DISTRIBUTIONS [J].
CHOW, CK ;
WAGNER, TJ .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1973, 19 (03) :369-371
[10]   THE COMPUTATIONAL-COMPLEXITY OF PROBABILISTIC INFERENCE USING BAYESIAN BELIEF NETWORKS [J].
COOPER, GF .
ARTIFICIAL INTELLIGENCE, 1990, 42 (2-3) :393-405
12345