Experiments with a component theory of probabilistic information retrieval based on single terms as document components

ABSTRACT

A component theory of information retrieval using single content terms as component for queries and documents was reviewed and experimented with. The theory has the advantages of being able to (1) bootstrap itself, that is, define initial term weights naturally based on the fact that items are self relevent; (2) make use of within-item term frequencies; (3) account for query-focused and document-focused indexing and retrieval strategies cooperatively; and (4) allow for component-specific feedback if such information is available. Retrieval results with four collections support the effectiveness of all the first three aspects, except for predictive retrieval. At the initial indexing stage, the retrieval theory performed much more consistantly across collections than croft's model and provided results comparable to Salton's tf*idf approach. An inverse collection term frequency (ICTF) formula was also tested that performed much better than the inverse document frequency (IDF). With full feedback retrospective retrieval, the component theory performed substantially better than Croft's, because of the highly specific nature of document-focused feedback. Repetitive retireval results with partial relevance feedback mirrored those for the retrospective. However, for the important case of predictive retrieval using residual ranking, results were not unequivocal.

REFERENCES

• 1: BELKIN, N. J., ODDY, R. N., AND BROOKS, H.M. ASK for information retrieval: Part I. J. Doc. 38 (1982), 61-71.
• 2: BELKIN, N. J., ODDY, R. N., AND BROOKS, H.M. ASK for information retrieval: Part II. J. Doc. 38 (1982), 145-164.
• 3: Abraham Bookstein , Don Kraft, Operations Research Applied to Document Indexing and Retrieval Decisions, Journal of the ACM (JACM), v.24 n.3, p.418-427, July 1977 [doi>10.1145/322017.322022]
• 4: BOOKSTEIN, A., AND SWANSON, D.R. A decision theoretic foundation for indexing. J. ASIS. 26 (1975), 45-50.
• 5: D. Chow , C. T. Yu, On the Construction of Feedback Queries, Journal of the ACM (JACM), v.29 n.1, p.127-151, Jan. 1982 [doi>10.1145/322290.322299]
• 6: CROFT, W.B. Experiments with representation in a document retrieval system. Inf. Tech. R&D. 2 (1983), 1-21.
• 7: CROFT, W. B., AND HARPER, D.J. Using probabilistic models of document retrieval without relevance information. J. Doc. 35 (1979), 285-295.
• 8: W. B. Croft , T. J. Lucia , J. Cringean , P. Willett, Retrieving documents by plausible inference: an experimental study, Information Processing and Management: an International Journal, v.25 n.6, p.599-614, 1989 [doi>10.1016/0306-4573(89)90095-2]
• 9: W. B. Croft , R. H. Thompson, I3R: a new approach to the design of document retrieval systems, Journal of the American Society for Information Science, v.38 n.6, p.389-404, Nov. 1987 [doi>10.1002/(SICI)1097-4571(198711)38:6<389::AID-ASI1>3.0.CO;2-4]
• 10: DUDA, R. O., AND HART, P.E. Pattern Classification and Scene Analysis. Wiley-Interscience, New York, 1973.
• 11: FAGAN, J. Experiments in automatic phrase indexing for document retrieval: A comparison of syntactic and non-syntactic methods. Ph.D. thesis, Dept. of Computer Science, Cornell Univ., Ithaca, N.Y.
• 12: FEINMAN, R. D., AND KWOK, K. L. Automatic classification of scientific documents by means of self-generated groups employing free language. J. ASIS. 24 (1973), 382-396.
• 13: Edward A. Fox, Development of the CODER system: a testbed for artificial intelligence methods in information retrieval, Information Processing and Management: an International Journal, v.23 n.4, p.341-366, July 1987 [doi>10.1016/0306-4573(87)90022-7]
• 14: E. A. Fox , G. L. Nunn , W. C. Lee, Coefficients of combining concept classes in a collection, Proceedings of the 11th annual international ACM SIGIR conference on Research and development in information retrieval, p.291-307, May 1988, Grenoble, France [doi>10.1145/62437.62465]
• 15: Norbert Fuhr, Models for retrieval with probabilistic indexing, Information Processing and Management: an International Journal, v.25 n.1, p.55-72, 1989 [doi>10.1016/0306-4573(89)90091-5]
• 16: Norbert Fuhr, Optimum polynomial retrieval functions based on the probability ranking principle, ACM Transactions on Information Systems (TOIS), v.7 n.3, p.183-204, July 1989 [doi>10.1145/65943.65944]
• 17: HARPER, D. J., AND VAN RIJSBERGEN, C.J. An evaluation of feedback in document retrieval using co-occurrence data. J. Doc. 34 (1978), 189-216.
• 18: HARTER, S.P. A probabilistic approach to automatic keyword indexing. Part 2: An algorithm for probabilistic indexing. J. ASIS. 26 (1975), 280-289.
• 19: KATZER, J., MCGILL, M. J., TESSIER, J. A., FRAKES, W., AND DASGUPTA, P. A study of the overlap among document representations. Inf. Tech. 1 (1982), 261-274.
• 20: KEMP, D. A. Relevance, pertinence and information system development. Inf. Storage Retrieval 10 (1974), 37-47.
• 21: K L Kwok, A probabilistic theory of indexing and similarity measure based on cited and citing documents, Journal of the American Society for Information Science, v.36 n.5, p.342-351, Sept. 1985 [doi>10.1002/asi.4630360510]
• 22: K. L. Kwok, An interpretation of index term weighting schemes based on document components, Proceedings of the 9th annual international ACM SIGIR conference on Research and development in information retrieval, p.275-283, September 1986, Palazzo dei Congressi, Pisa, Italy [doi>10.1145/253168.253226]
• 23: K. L. Kwok, A neural network for probabilistic information retrieval, Proceedings of the 12th annual international ACM SIGIR conference on Research and development in information retrieval, p.21-30, June 25-28, 1989, Cambridge, Massachusetts, United States
• 24: KWOK, K.L. Application of neural network to information retrieval. In Proceeding of the International Joint Conference on Neural Networks (Washington D.C. Jan. 1990). M. Caudill, Ed., Erlbaum, N.J., 1990, pp. 623-626.
• 25: K. L. Kwok , William Kuan, Experiments with document components for indexing and retrieval, Information Processing and Management: an International Journal, v.24 n.4, p.405-417, May 1988 [doi>10.1016/0306-4573(88)90044-1]
• 26: D. D. Lewis , W. B. Croft, Term clustering of syntactic phrases, Proceedings of the 13th annual international ACM SIGIR conference on Research and development in information retrieval, p.385-404, September 05-07, 1990, Brussels, Belgium [doi>10.1145/96749.98244]
• 27: 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]
• 28: ROBERTSON, S.E. The probability ranking principle in IR. J. Doc. 33 (1977), 294-304.
• 29: ROBER'rSON, S. E., MARON, M. E., AND COOPER, W.S. Probability of relevance: A unification o\f two competing models for document retrieval. Inf. Tech. R&D. 1 (1982), 1-21.
• 30: ROBERTSON, S. E., AND SPARCK JONES, K. Relevance weighting of search terms. J. ASIS. 27 (1976), 129-146.
• 31: 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
• 32: Gerard Salton , Christopher Buckley, Term-weighting approaches in automatic text retrieval, Information Processing and Management: an International Journal, v.24 n.5, p.513-523, 1988 [doi>10.1016/0306-4573(88)90021-0]
• 33: SALTON, G., Wu, H., AND Yu, C. W. The measurement of term importance in automatic indexing. J. ASIS 32 (1981), 175-186.
• 34: SARACEVm, T. Relevance: A review of and a framework for the thinking on the notion in information science. J. ASIS. 26 (19'75), 321-343.
• 35: SMEATON, A. F., AND VAN RIJSBERGEN, C.J. The retrieval effects of query expansion on a feedback document retrieval system. Computer J. 26 (1983), 239-246.
• 36: SPARCK JONES, K. A statistical interpretation of term specificity and its application in retrieval. J. Doc. 8 (1972), 11-21.
• 37: SPARCK JONES, K. Experiments in rei.evance weighting of search terms. Inf. Proc. Manage. 15 (1979), 133-144.
• 38: VAN RIJSBERGEN, C.J. A theoretical basis for the use of co-occurrence data in information retrieval. J. Doc. 33 (1977), 106-119.
• 39: S. K. M. Wong , Y. Y. Yao, A probability distribution model for information retrieval, Information Processing and Management: an International Journal, v.25 n.1, p.39-53, 1989 [doi>10.1016/0306-4573(89)90090-3]
• 40: Yu, C. T., BUCKLEY, C., LAM, K., AND SALTON, G. A generalized term dependence model in information retrieval. Inf. Tech. R&I). 2 (1983), 129-154.
• 41: C. T. Yu , W. Meng , S. Park, A framework for effective retrieval, ACM Transactions on Database Systems (TODS), v.14 n.2, p.147-167, June 1989 [doi>10.1145/63500.63519]
• 42: C. T. Yu , G. Salton, Precision Weighting—An Effective Automatic Indexing Method, Journal of the ACM (JACM), v.23 n.1, p.76-88, Jan. 1976 [doi>10.1145/321921.321930]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Retrieval models

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing
          Subjects: Indexing methods

General Terms:
Design, Experimentation, Theory

Keywords:
document-focused and query-focused relevance feedback, indexing and retrieval, inverse collection term frequency weighting, inverse document frequency weighting, probabilistic indexing, probabilistic retrieval, ranking and weighting of composite objects