I am posting it here as i am not getting proper reply in the
Solr-user,......
Details
Query will be like "most"{t2,t3,t5,t6,t7} where "most" is linguistic
quantifier having some weights varying b/w a=0.3 and b=0.8
The relevancy matrix with corresponding tf*idf values for the above query is
R(relevancy Matrix)
t2 t3 t5 t6 t7
d1 0.6 0.0 0.4 0.2 0.4
d2 0.4 0.1 0.7 0.6 0.0
d3 0.2 0.5 0.0 0.3 0.6
d4 0.5 0.3 0.5 0.4 0.1
Difficulty 1- How to get the above tf*idf score for all the terms in
relevant document
Using a formulae we can calculate the 5 weights as
w1=0.0,w2=0.2,w3=0.4,w4=0.4,w5=0.0
After calcualting the weights , we can multiply the terms score of each
document with weights in decreasing order( eg. for 1st document- 0.6, then
0.4, 0.4 , 0.2 , then 0.0)
This multiplication of matrix is like
(m*n)*(n*1) ---> n*1 signifies single column matrix of 5 weights defined
above
After multiplication we get result in matrix with single row called as
Query -relevancy matrix
QR=
d1 0.0*0.6+0.2*0.4+0.4*0.4+0.4*0.2+0.0*0.0
d2 0.0*0.7+0.2*0.6+0.4*0.4+0.4*0.1+0.0*0.0
d3 0.0*0.6+0.2*0.5+0.4*0.3+0.4*0.2+0.0*0.0
d4 0.0*0.5+0.2*0.5+0.4*0.4+0.4*0.3+0.0*0.1
=
d1 0.32
d2 0.32
d3 0.30
d4 0.38
difficulty 2 - where should i multiply this matrix and add to the solr?
Hence final order of documents on the basis of final score is
0.38>0.32>=0.32>0.30
d4>d1>=d2>d3
Please guide me .
-----
Kumar Anurag
--
View this message in context:
http://lucene.472066.n3.nabble.com/Embedding-own-Fuzzy-code-to-Solr-tp2701425p2701425.html
Sent from the Solr - Dev mailing list archive at Nabble.com.
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
