A WebPage Content Block Detection Method Based on Layout Features and Languages Features

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 自然语言处理

	A WebPage Content Block Detection Method Based on Layout Features and Languages Features
	Han Xianpei; Liu Kang; Zhao Jun
发表期刊	Chinese Journal of Computers
	2008
期号	22 页码:15-21
摘要	This paper analyzed the different feature types of web-page blocks, and presented a Web-page content block detection method based on layout features and language features, which effectively resolved the seesaw problem between detection accuracy and model generality across different types of web-pages. The method used the vision-block tree to represent web-page, built two individual classifiers respectively for web-page’s layout features and language features, and used different strategies to combine these two classifiers. The experimental results show that, with holding the content block detection recall higher than 90%, thecombined classifiers’ accuracy can reach 85 percents, 5 percents higher than the classifier using only the layout features, and 15 percents higher than the classifier using only the language features; and the experimental results also show that the combined classifiers obtained good detection performance over five selected websites which means that it have good generality.
关键词	Web-page Cleaning
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40979
专题	多模态人工智能系统全国重点实验室_自然语言处理
推荐引用方式 GB/T 7714	Han Xianpei,Liu Kang,Zhao Jun. A WebPage Content Block Detection Method Based on Layout Features and Languages Features[J]. Chinese Journal of Computers,2008(22):15-21.
APA	Han Xianpei,Liu Kang,&Zhao Jun.(2008).A WebPage Content Block Detection Method Based on Layout Features and Languages Features.Chinese Journal of Computers(22),15-21.
MLA	Han Xianpei,et al."A WebPage Content Block Detection Method Based on Layout Features and Languages Features".Chinese Journal of Computers .22(2008):15-21.