Abstract | ||
---|---|---|
In order to evaluate the security rank of document owner (sender or Web station), the documents discrimination is widely adopted to classify Web documents. The old strategy based on keywords matching often leads to low precision. This article proposes a new model called CKPU (Classifying by key Phrase Understanding) including the key sentence template, mining threshold vector, objective and, subjective discriminating. The experiment result shows that the algorithms are efficient for discriminating documents. |
Year | DOI | Venue |
---|---|---|
2001 | 10.1007/3-540-47714-4_8 | WAIM |
Keywords | Field | DocType |
mining threshold vector,key phrase understanding,web document,document owner,key sentence template,documents discrimination,new model,experiment result,classify web document,low precision,web station | Data mining,Web document,Information retrieval,Computer science,Document processing,Image processing,Phrase,Communication source,Sentence,The Internet | Conference |
Volume | ISSN | ISBN |
2118 | 0302-9743 | 3-540-42298-6 |
Citations | PageRank | References |
1 | 0.37 | 2 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Changjie Tang | 1 | 483 | 62.75 |
Tong Li | 2 | 10 | 11.59 |
Changyu Liu | 3 | 71 | 4.49 |
Yin Ge | 4 | 20 | 1.95 |