Abstract | ||
---|---|---|
Abstract There,is strong,empirical,and,theoretic,evidence,that,com- bination,of retrieval,methods,can,improve,performance.,In this paper, we systematically compare combination strate- gies in the context of document filtering, using queries from the,Tipster,reference,corpus.,We,find,that,simple,averag- ing strategies do indeed improve performance, but that di- reet,averaging,of probability,estimates,is not,the,correet approach. Instead, the probabiJit y estimates must be renor- malized,using,logistic,regression,on,the,known,relevance judgments.,We examine,more,complex,combination,strat~ gies but find them,less successful,due,to the high,correlations among,our,filtering,methods,which,are,optimized,over,the same,training,data,and,employ,similar,document,represert- tations. 1,Introduction A text,filtering,system,monitors,au,incoming,document |
Year | DOI | Venue |
---|---|---|
1996 | 10.1145/243199.243275 | SIGIR |
Keywords | Field | DocType |
method combination,logistic regression | Data mining,Computer science,Multinomial logistic regression,Logistic model tree,Document filtering,Logistic regression | Conference |
ISBN | Citations | PageRank |
0-89791-792-8 | 68 | 12.69 |
References | Authors | |
31 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
David A. Hull | 1 | 1282 | 214.27 |
Jan O. Pedersen | 2 | 6301 | 1177.07 |
Hinrich Schütze | 3 | 2113 | 362.21 |