109
retrieval. There are, however, a few specialist references worth mentioning.

Anew classic paper on the limitations of a Boolean search is Verhoeff et al.[18]. Miller[19] has tried to get away from a simple Boolean search by introducing a form of weighting although maintaining essentially a Boolean search. Angione[20] discusses the equivalence of Boolean and weighted searching. Rickman[21] has described a way of introducing automatic feedback into a Boolean search. Goffman[22] has investigated an interesting search strategy based on the idea that the relevance of a document to a query is conditional on the relevance of other documents to that query. In an early paper by Hyvarinen[23], one will find an information-theoretic definition of the 'typical member' cluster representative. Negoita[24] gives a theoretical discussion of a bottom-up search strategy in the context of cluster-based retrieval. Much of the early work on relevance feedback done on the SMART project has now been reprinted in Salton[25]. Two other independence pieces of work on feedback are Stanfel[26] and Bono[27].

References

1. KNUTH, D.E., The Art of Computer Programming, Vol. 3, Sorting and Searching, Addison-Wesley, Reading, Massachusetts (1973).

2. SALTON, G., Automatic Information Organisation and Retrieval, McGraw-Hill, New York (1968).

3. van RIJSBERGEN, C.J., 'The best-match problem in document retrieval', Communications of the ACM, 17, 648-649 (1974).

4. van RIJSBERGEN, C.J., 'Further experiments with hierarchic clustering in document retrieval', Information Storage and Retrieval, 10, 1-14 (1974).

5. MURRAY, D.M., 'Document retrieval based on clustered files', Ph.D. Thesis, Cornell University Report ISR-20 to National Science Foundation and to the National Library of Medicine (1972).

6. GOWER, J.C., 'Maximal predictive classification', Biometrics, 30, 643-654 (1974).

7. CROFT, W.B., Organizing and Searching Large Files of Document Descriptions, Ph.D. Thesis, University of Cambridge (1979).

8. YU, C.T., and LUK, W.S., 'Analysis of effectiveness of retrieval in clustered files', Journal of the ACM, 24, 607-622 (1977).

9. YU, C.T., LUK, W.C. and SIU, M.K., 'On the estimation of the number of desired records with respect to a given party' (in preparation).

10. ARNAUDOV, D.D.. and GOVORUN, N.N. Some Aspects of the File Organisation and Retrieval Strategy in Large Databases, Joint Institute for Nuclear Research, Dubna (1977).

11. Medline Reference Manual, Medlars Management Section, Bibliographic Services Division, National Library of Medicine.

12. BARRACLOUGH, E.D., MEDLARS on-linesearch formulation and indexing, Technical Report Series,No. 34, Computing Laboratory, University of Newcastle upon Tyne.

109