next up previous
Next: 15.2.1 Vector similarity Up: Topics in Information Retrival Previous: 15.1.3 The probability ranking

15.2 The Vector Space Model

  奈良 京都 大阪 神戸 東京 $\cdots$ 福岡  
Doc 1   1   1        
Doc 2     1   3   1  
Doc 3   2         1  
Doc 4 1     2 1      
Doc 5 2     1     1  
$\vdots$                
Doc N   1   3     1  






検索要求ベクトル $\vec{q}$ = {(1 $\cdot$ 奈良), (2 $\cdot$ 京都), (1 $\cdot$ 神戸)}



SIM(q,Doc 1) = 1 $\cdot$ 0 + 2 $\cdot$ 1 + 1 $\cdot$ 1 = 3  
SIM(q,Doc 2) = 1 $\cdot$ 0 + 2 $\cdot$ 0 + 1 $\cdot$ 0 = 0  
SIM(q,Doc 3) = 1 $\cdot$ 0 + 2 $\cdot$ 2 + 1 $\cdot$ 0 = 4  
SIM(q,Doc 4) = 1 $\cdot$ 1 + 2 $\cdot$ 0 + 1 $\cdot$ 2 = 3  
SIM(q,Doc 5) = 1 $\cdot$ 2 + 2 $\cdot$ 0 + 1 $\cdot$ 1 = 3  
$\vdots$          
SIM(q,Doc N) = 1 $\cdot$ 0 + 2 $\cdot$ 1 + 1 $\cdot$ 3 = 5  
 



 
next up previous
Next: 15.2.1 Vector similarity Up: Topics in Information Retrival Previous: 15.1.3 The probability ranking

1999-08-03