David M. Jackson
ABSTRACT
A particular classification and retrieval model are considered. A notion is introduced which indicates the extent to which retrieval performance may be improved by a suitable choice of classification within the model. A method for determining the optimal performance for the model is outlined together with an algorithm for constructing the classification which allows this limit to be attained. A treatment of the mathematical preliminaries for a particular class of match function is given. The relevance of the analysis in research on information retrieval systems is discussed.
- Cleverdon, C. W. and Keen, M. Factors determining the performance of indexing systems, ASLIB Cranfield Research Project, 1966, Vols. 1 and 2.Google Scholar
- Doyle, L. B. Semantic road maps for literature searchers, Journal of the ACM 8, 1961, pp. 553-578. Google ScholarDigital Library
- Doyle, L. B. Indexing and abstracting by association, American Documentation 13, 1962, pp. 378-390.Google ScholarCross Ref
- Evans, T. G. A heuristic program to solve geometric-analogy problems, American Federation of Information Processing Societies, AFIPS Conference Proceedings, Vol. 25; 1964 Spring Joint Computer Conference, Washington, April 1964, pp. 327-338.Google Scholar
- Gleason, A. M. A search problem in the n-cube, Proceedings of Symposia in Applied Mathematics 10, Combinatorial Analysis, 1960, pp. 175-178.Google ScholarCross Ref
- Hartigan, J. A. Representation of similarity matrices by trees, Journal of the American Statistical Association 62, 1967, pp. 1140-1158.Google ScholarCross Ref
- Jackson, D. M. A note on set of functions for information retrieval, Information Storage and Retrieval 5, 1969, pp. 27-41.Google ScholarCross Ref
- Jackson, D. M. Classification, relevance and information retrieval, in Advances in Computers, Vol. 11, M. C. Yovits, Ed., Academic Press, New York, (forthcoming).Google Scholar
- Jackson, D. M. Basis for an improvability measures in information retrieval, in American Society for Information Science Annual Meeting, 32nd, San Francisco, October 1-4, 1969, Proceedings, Vol. 6, pp. 487-495.Google Scholar
- Nagy, G. State of the art in pattern recognition, Proceedings of the IEEE 56, 1968, pp. 836-863.Google ScholarCross Ref
- Resnick, A. and Savage, T. T. The consistency of human judgements of relevance, American Documentation 15, 1964, pp. 93-95.Google ScholarCross Ref
- Salton, G. Computer evaluation for indexing and text processing, Journal of the ACM 15, 1968, pp. 8-36. Google ScholarDigital Library
- Salton, G. and Lesk M. E. The SMART automatic document retrieval system - an illustration, Communications of the ACM 8, 1965, pp. 391-398. Google ScholarDigital Library
- Salton, G. and Lesk, M. E. Relevance assessments and retrieval system evaluation, Information Storage and Retrieval 4, 1969, pp. 343-359.Google Scholar
- Sparck Jones, K. and Jackson, D. M. Current approaches to classification and clump-finding at the CLRU, Computer Journal 10, 1967, pp. 29-37.Google ScholarCross Ref
- Swets, J. A. Effectiveness of information retrieval methods, Report No. 1499, Bolt, Beranek and Newman, Cambridge, Mass, 1967.Google Scholar
- Taube, M. A note on the pseudo-mathematics of relevance, American Documentation 16, 1965, pp. 69-72.Google ScholarCross Ref
Recommendations
Improved classification with allocation method and multiple classifiers
We propose a new allocation method for building a classification ensemble.Allocation method uses multiple classifiers: the allocator and micro classifiers.Allocator separates the dataset and allocates them to one of micro classifiers.Allocator is based ...
A Combined Classification Algorithm Based on C4.5 and NB
ISICA '08: Proceedings of the 3rd International Symposium on Advances in Computation and IntelligenceWhen our learning task is to build a model with accurate classification, C4.5 and NB are two very important algorithms for achieving this task because of their simplicity and high performance. In this paper, we present a combined classification ...
Switching class labels to generate classification ensembles
Ensembles that combine the decisions of classifiers generated by using perturbed versions of the training set where the classes of the training examples are randomly switched can produce a significant error reduction, provided that large numbers of ...
Comments