Two models of retrieval with probabilistic indexing

ABSTRACT

We describe two retrieval models for probabilistic indexing. The binary independence indexing (BII) model is a generalized version of the Maron & Kuhns indexing model. In this model, the indexing weight of a descriptor in a document is an estimate of the probability of relevance of this document with respect to queries using this descriptor. The retrieval-with-probabilistic-indexing (RPI) model is suited to different kinds of probabilistic indexing. Therefore we assume that each indexing model has its own concept of 'correctness' to which the probabilities relate. The concept of correctness is not necessarily identical with the concept of relevance, it is only required to depend on relevance. In addition to the probabilistic indexing weights, the RPI model provides the possibility of relevance weighting of search terms. Both retrieval models are compared in experiments, showing equally good results.

REFERENCES

• BOOK74: Bookstein, A., Swanson, D.R., aProbabilistic models for automatic indexing=, Journal of the American Society for Information Science 25, pp. 312-318.
• BOOK75: Bookstein, A., Swanson, D.R., "A Decision Theoretic Foundation for Indexing', Journal of the American Society for Information Science 26, pp. 45-50.
• BOOK83: Bookstein, A., "Outline of a General Probabilistic Retrieval Mocle}#, Journal of Documentation 39(2), pp. 63-7Z.
• FUHR84: N. Fuhr , G. E. Knorz, Retrieval test evaluation of a rule based automatic indexing (AIR/PHYS), Proc. of the third joint BCS and ACM symposium on Research and development in information retrieval, p.391-408, November 1984, King's College, Cambridge
• FUHR85: Fuhr, N., "A probabilktic model of dictionary based automatic indexing', Proceedings of the riso 85, Recherche d'Informations AssktSe par Ordinateur, pp. 20'/-216.
• HART75: Hatter, S.D., "Probabilistic Approach to Automatic Keyword Indexing, Part I: On the Dktribution of Speciality Words in a Technical Literature, Part H: An Algorithm for Probabilistic Indexings, Journal of the American Society for Information Science 26, pp. 197-#06, 280-280.
• KNOR83a: Knorz, G., "Automafisches Indexieren als Erkennen ahstrakter Objekte# Sprache und Information, Band 8. Nemeyer, T#bingen.
• KNOR83b: Knots, O., "Development of automatic indexing for the AIR retrieval test', Experiments by means of ALIBABA. Internal Report DVII 83-3, TH Darmstadt, Fachberelch Informatik, Fachgeb|et Datenverwaltungmrystriae 2.
• MARO60: M. E. Maron , J. L. Kuhns, On Relevance, Probabilistic Indexing and Information Retrieval, Journal of the ACM (JACM), v.7 n.3, p.216-244, July 1960 [doi>10.1145/321033.321035]
• MARO82: M. E. Maron, Probabilistic approaches to the document retrieval problem, Proceedings of the 5th annual ACM conference on Research and development in information retrieval, p.98-107, May 18-20, 1982, West Berlin, Germany
• ROBE81: S. E. Robertson , C. J. van Rijsbergen , M. F. Porter, Probabilistic models of indexing and searching, Proceedings of the 3rd annual ACM conference on Research and development in information retrieval, p.35-56, June 23-27, 1980, Cambridge, England
• ROBE82: Robertsou, S.E., Maron, M.E., Cooper, W.S., "Probability of relevance: A unification of two competing models for document retrieval. Information Technology: Research and Development 1, pp. 1-21.
• ROBE84: Robertson, S.E., Harding, P., "Prob#bilisti~ automatic indexing by learning from human indexers', journal of Documentation 40(4), pp. 264-270.