A Web Text De-Noising Algorithm Based on Machine Learning
Xiao Le · Applied Mechanics and Materials · 2014
The Web has become a huge information resources distributed information space, contains a huge amount of various types of Web documents.Search engine, it is difficult to meet different user requirements for the elaboration of the retrieval results.To noise method, this paper proposes a text first to find out the noise page information, then according to the rules of human interaction way to generate a denoising, finally find and remove the noise, the experiments has been proved this method to be effective on improving the accuracy of classification.