COOPER, W. S., CHEN, A., AND GEY, F. C. Full text retrieval based on probalistic equations with coefficients fitted by logistic regression. In Harman [12], pp. 57--66. 6 http://www.lexiquest.com IRSG 2000 - 22nd Annual Colloquium on IR Research 8 Learning in Information Retrieval: a Probabilistic Differential Approach  Home/Search   Document Not in Database   Summary   Related Articles

....given some quantitative variables on the document and query relationship (like scores of some Vector Space Model similarity measures) which may contribute to the prediction. Two different approaches exist: linear regression methods (Fuhr et al. 11] and logistic regression methods (Cooper et al. [9]) The latter approach, as it gives results in the interval [0: 1] is more appropriate for the probabilistic framework. We can also cite Yu and Raghavan [24] who propose to build semantic relationships with feedback. The basic idea is that each query feature that is not present in a relevant ....

COOPER, W. S., CHEN, A., AND GEY, F. C. Full text retrieval based on probalistic equations with coefficients fitted by logistic regression. In Harman [12], pp. 57--66. 6 http://www.lexiquest.com IRSG 2000 - 22nd Annual Colloquium on IR Research 8 Learning in Information Retrieval: a Probabilistic Differential Approach

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC