A connectionist approach to conceptual information retrieval

ABSTRACT

This report proposes that recent advances using low-level connectionist representations offer new possibilities to those interested in free text information retrieval (IR). The AIR system demonstrates that this representation suits the IR domain well, particularly the special problems attending the more sophisticated forms of conceptual retrieval required in legal applications. Also, the natural way in which connectionist representations allow learning means that AIR can avoid the high costs associated with manual indexing while providing comparable results. The paper begins by motivating the importance of legal information retrieval, from the perspectives of both the Law and artificial intelligence (AI). Our approach is then compared to traditional methods for IR, and to more recent work using higher-level symbolic representations from AL After a brief introduction to connectionist representations in general, the AIR system is presented. The paper closes with evidence that this system does, in fact, begin to support the use of those “open textured” concepts that make the Law both a very difficult and a very illuminating domain for AI research.

REFERENCES

• 1: L.E. Allen. Laxtguage, law and logic: plain legal drafting for the modern age. In B Niblett, editor, ComImter science and law, Cambridge Umversity Press, Cambridge, England, 1980. normalization.
• 2: J.A. Anderson and G.E. Hinton. Models of information processing in the brain, in G.E. Hinton and J.A Anderson, editors, Parallel models of associative memory Lawrence Erlbaum Assoc., Hills-dale, NJ, 1984. distributed representation; activity patterns.
• 3: Richard Kuehn Belew, Adaptive information retrieval: machine learning in associative networks (connectionist, free-text, browsing, feedback), 1986
• 4: David C. Blair , M. E. Maron, An evaluation of retrieval effectiveness for a full-text document-retrieval system, Communications of the ACM, v.28 n.3, p.289-299, March 1985 [doi>10.1145/3166.3197]
• 5: R.J. Brachman. What isa is and isn't: an analysis of taxonomic links in semantic nets. Computer, 1983.
• 6: B.G. Buchanan and T.E. Headrick. Some speculation about artificial intelligence and legal reasoning. Stanford Law Review, 1970.
• 7: Benjamin Nathan Cardozo. The nature of the judicial process. Yale university press, New Haven, CN, 1921.
• 8: Constantino Ciampi, Deirdre Exell Pirro, Ello Fameli, and Giuzeppe Trivisonno. Thes/bid: an expert system for constructing a computer-based thesaurus for legal informatics and computer law. In Charles Walter, editor, Computing Power and Legal Reasoning, pages 375--412, West Publishing Co., 1985.
• 9: Lee D. Erman , Frederick Hayes-Roth , Victor R. Lesser , D. Raj Reddy, The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty, ACM Computing Surveys (CSUR), v.12 n.2, p.213-253, June 1980 [doi>10.1145/356810.356816]
• 10: S.E. Fahlman. NETL: a system for representing and using real world knowledge. MIT Press, Cambridge, MA, 1979. virtual copy; marker passing; primitive link-types; parcel network; instance v. role.
• 11: Grayfred Grey. Law & technology conference expert system workshop. In Charles Walter, editor, Computing Power and Zegal Reasoning, pages 621-626, West Publishing Co., 1985.
• 12: Carole Diane Hafner, An information retrieval system based on a computer model of legal knowledge., 1978
• 13: Micheal Heather. Demand-driven model for a half-intelligent system. In Charles Walter, editor, Computing Power and Legal Reasoning, pages 69-103, West Publishing Co., 1985.
• 14: G. E. Hinton , T. J. Sejnowski, Learning and relearning in Boltzmann machines, Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations, MIT Press, Cambridge, MA, 1986
• 15: G.E. Hinton, T.J. Sejnowski, stud D.H. Ackley. Boltzman machines: Constrait satisfaction networks that learn. Technical Report CMU-C5-84-119, DepL Computer Science, Carnegie-Mellon University, 1984. annealing.
• 16: W. James. The principles of psychology. Dover, New York, 1890.
• 17: W. James. Psychology (Briefer course). Collier Books, New York,1893.
• 18: Robert Krovetz. The use of knowledge representation formalisms in the modeling of legal concepts. In Charles Walter, editor, Computing Power and Legal Reasoning, pages 275-317, West Publishing Co., 1985.
• 19: L.T. McCarty. The taxman project: towards a cognitive theory of legal argument. In B Niblett, editor, Computer science and law, Cambridge University Press, Cambridge, England, 1980. proto- type deformation.
• 20: David E. Rumelhart , James L. McClelland , CORPORATE PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition, vol. 2: psychological and biological models, MIT Press, Cambridge, MA, 1986
• 21: W.S. McCullough and W.H. Pitts. A logical calculus of ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 1943.
• 22: J.A. Meldman. Decision support systems for legal research and analysis. Technical Report 1039-79, Sloan School, MIT, Cambridge, MA, 1977. legal reasoning.
• 23: Perceptrons: An Introduction to Computational Geometry, The MIT Press, 1969
• 24: M.C. Mozer. Inductive information retrieval ssing parallel distributed computation. Technical Report, inst. Cognitive Science, UCSD, La Jolla, CA, 1984.
• 25: Allen Newell. Physical symbol systems. Cognitive Science, 4:135-183, 1980.
• 26: F. Rosenblatt. Principles of neurodynamics: Perceptons and the theory of brain mechanisms. Spartan Books, Washington, D.C., 1962. perceptron.
• 27: D.E. Rumelhart, G.E. Hinton, and R.J. Williams. Learning international representations by error propagation. Technical Report ICS-8506, Iustitute for Cognitive Science, UCSD, La 3olla, CA, 1985. feed-forward networks; semi-linear propagation; feedback propagation.
• 28: 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
• 29: G. Salton and M.J. McGiLL Introduction retrieval McGraw-Hill, Inc., New York, NY, 1983.
• 30: J.A. Sprowl. Lexi, v. westlaw: computer-assisted legal research comes of age. lllinois Bar Journal 1979. LEXIS; WESTLAW.
• 31: R.K. Stampner. Legol: modelling Legal rules by computez. In B. Niblett, editor, Computer science and law, Cambridse University Press, Cambridse, Ensland, 1980. structure; data normalization; action; definition.
• 32: C. Tapper. Citations as a tool for serching the law by computer. In B Niblett, editor, Computer science and law, Cambridge University Press, Cambridge, England, 1980.
• 33: Anne Von Der Lieth Gardner, An artificial intelligence approach to legal reasoning, 1984
• 34: Anne von der Lieth Gardner, An artificial intelligence approach to legal reasoning, MIT Press, Cambridge, MA, 1987
• 35: Terry Winograd, Language As a Cognitive Process: Syntax, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1982

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

Additional Classification:
  H. Information Systems
  H.1 MODELS AND PRINCIPLES
      H.1.2 User/Machine Systems
          Subjects: Human information processing
  H.2 DATABASE MANAGEMENT
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Retrieval models

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.1 Applications and Expert Systems
          Subjects: Law

General Terms:
Design, Experimentation, Human Factors