Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

AIR represents a connectionist approach to the task of information retrieval. The system uses relevance feedback from its users to change its representation of authors, index terms and documents so that, over time, AIR improves at its task. The result is a representation of the consensual meaning of keywords and documents shared by some group of users. The central focus goal of this paper is to use our experience with AIR to highlight those characteristics of connectionist representations that make them particularly appropriate for IR applications. We argue that this associative representation is a natural generalization of traditional IR techniques, and that connectionist learning techniques are effective in this setting.

REFERENCES

• 1: Richard Kuehn Belew, Adaptive information retrieval: machine learning in associative networks (connectionist, free-text, browsing, feedback), 1986
• 2: R.K. Belew. Designing appropriate learning rules for connectionist sytems. In Proc. IEEE Intl. Conf. on Neural Networks, June 1987.
• 3: I#.K. Belew and D.E. Rose. Learning semantics from word use. (unpublished manuscript), 1989.
• 4: R. J. Brachman , D. L. McGuinness, Knowledge representation, connectionism and conceptual retrieval, Proceedings of the 11th annual international ACM SIGIR conference on Research and development in information retrieval, p.161-174, May 1988, Grenoble, France [doi>10.1145/62437.62448]
• 5: T.L. Brauen. Document vector modification. In G. Salton, editor, The SMART retrieval system, chapter 24. Prentice-Hall, New Jersey, 1969.
• 6: Paul R. Cohen , Rick Kjeldsen, Information retrieval by constrained spreading activation in semantic networks, Information Processing and Management: an International Journal, v.23 n.4, p.255-268, July 1987 [doi>10.1016/0306-4573(87)90017-3]
• 7: M.A. Derthick. A connectionist architecture for representing and reasoning about structured knowledge. In Proc. 9th Conf. of the Cognitive Science Society, July 1987.
• 8: Lauren B. Doyle, Semantic Road Maps for Literature Searchers, Journal of the ACM (JACM), v.8 n.4, p.553-578, Oct. 1961 [doi>10.1145/321088.321095]
• 9: L.B. Doyle. Indexing and abstracting by association. American Documentation, 1962.
• 10: S.E. Fahlman. NETL: a system for representing and using real-world knowledge. MIT Press, Cambridge, MA, 1979.
• 11: S.R. Friedman, J.A. Maceyak, and S.F. Weiss. A relevance feedback system based on document transformations. In G. Salton, editor, The SMART retrieval system, chapter 23. Prentice- Hall, New Jersey, 1967.
• 12: James A. Anderson , Geoffrey E. Hinton, Parallel Models of Associative Memory, Lawrence Erlbaum Associates, Inc., Mahwah, NJ, 1989
• 13: G. E. Hinton, Connectionist learning procedures, Artificial Intelligence, v.40 n.1-3, p.185-234, Sep. 1989 [doi>10.1016/0004-3702(89)90049-0]
• 14: J.L. McClelland and D.E. Rumelhart. An interactive activation model of the effect of context on language learning (part 1). Psychological Review, 1981.
• 15: M.C. Mozer. Inductive information retrieval using parallel distributed computation. Technical report, Inst. Cognitive Science, UCSD, La Jolla, CA, 1984.
• 16: Judea Pearl, Probabilistic reasoning in intelligent systems: networks of plausible inference, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1988
• 17: Scott Everett Preece, A spreading activation network model for information retrieval, 1981
• 18: D.E. Rose and R.K. Belew. A case for symbolic/sub-symbolic hybrids. In Proc. Cognitive Science Society, 1989. (submitted).
• 19: D. E. Rose , R. K. Belew, Legal information retrieval a hybrid approach, Proceedings of the 2nd international conference on Artificial intelligence and law, p.138-146, May 1989, Vancouver, British Columbia, Canada [doi>10.1145/74014.74033]
• 20: D.E. Rose and R.K. Belew. Toward a directmanipulation interface for conceptual information retrieval. In Proc. ASIS Mid-year meeting, 1989. (to appear).
• 21: D. E. Rumelhart , G. E. Hinton , R. J. Williams, Learning internal representations by error propagation, Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations, MIT Press, Cambridge, MA, 1986
• 22: D.E. Rumelhart and J.L. McClelland. An interactive activation model of the effect of context in language learning (part 2). Psychological Review, 1981.
• 23: David E. Rumelhart , James L. McClelland , CORPORATE PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations, MIT Press, Cambridge, MA, 1986
• 24: Gerard Salton , Chris Buckley, On the Use of Spreading Activation Methods in Automatic Information Retrieval, Cornell University, Ithaca, NY, 1988
• 25: Gerard Salton , Michael J. McGill, Introduction to Modern Information Retrieval, McGraw-Hill, Inc., New York, NY, 1986
• 26: Gerard Salton , Chris Buckley, Parallel text search methods, Communications of the ACM, v.31 n.2, p.202-215, Feb. 1988 [doi>10.1145/42372.42380]
• 27: Craig Stanfill , Brewster Kahle, Parallel free-text search on the connection machine system, Communications of the ACM, v.29 n.12, p.1229-1239, Dec. 1986 [doi>10.1145/7902.7907]
• 28: H. Edmund Stiles, The Association Factor in Information Retrieval, Journal of the ACM (JACM), v.8 n.2, p.271-279, April 1961 [doi>10.1145/321062.321074]
• 29: Harold S. Stone, Parallel querying of large databases: a case study, Computer, v.20 n.10, p.11-21, Oct. 1987 [doi>10.1109/MC.1987.1663384]
• 30: David W. Tank , John J. Hopfield, Collective computation in neuronlike circuits, Scientific American, v.257 n.6, p.104-114, Dec. 1987 [doi>10.1038/scientificamerican1287-104]

INDEX TERMS

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

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

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.4 Knowledge Representation Formalisms and Methods
          Subjects: Representations (procedural and rule-based)
      I.2.6 Learning
          Subjects: Knowledge acquisition

General Terms:
Algorithms, Design