Context-sensitive learning methods for text categorization
SIGIR '96 Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval
Badness information audit based on image character filtering
ISPA'05 Proceedings of the 2005 international conference on Parallel and Distributed Processing and Applications
Hi-index | 0.00 |
It is difficult to collect information over Gigabit networks for infor-mation audit. In the paper, the information audit system adopts the network processor to collect and analyze the date in the low level of network. Through taking an advanced research on current algorithm, some improvements of the Bayes categorization algorithm have been made as well as the proposal of a text categorization model of the minimal risk Bayes decision. In addition, it considers the risk probability of mistaking the related text for unrelated text during the text categorization. The experiments results show that it promotes the precision of text categorization.