Case recognition and strategy classification

ABSTRACT

In a conventional expert system shell, the process of automated reasoning is generally determined by four components: the current fact situation, a goal, the content of the knowledge base, and control knowledge. This paper focuses on control knowledge. The approach taken is to obtain control knowledge from precedents which resemble the current fact situation. Control knowledge, which is here understood as both referring to search and strategy, is important because control knowledge: 1.-facilitates efficient problem solving; 1.-enables context sensitive and adequate questioning; and 3.-may actually determine the outcome of the reasoning process. With regard to the latter, we believe that one of the manifestations of the discretion a judge is provided with, is that judges often choose a particular control strategy in order to obtain a certain result. As a consequence the strategy followed is often very case-specific. If the aim of a LKBS is to simulate or predict the outcome in a particular problem situation, the system has to simulate or predict the control strategy in this specific case. The model presented uses precedents similar to the case at hand to obtain the applicable control strategy. Neural networks are used to find similar cases. One of the characteristics of the system presented, is, however, that the inferences made by neural networks are not a part of the final reasoning chain. The model is flexible in various ways. Firstly, the precedents may be applicable to a wider range of cases then the precise precedent represented in the case base. Secondly, since the precedent is a model for the control strategy rather than the solution of the case, the amount of problem solving that has to be one after case recognition may vary. This means that the precedent is a model for the type of problem solving and that the specifics of the current case may still determine the precise outcome. Thirdly, since the control strategy determines which questions the system will ask, the recognition method is able to suggest a similar case with the applicable control strategy in a very early stage of problem solving, i.e. before all information is available.

REFERENCES

• 1: Aikens, J.S. (1980) Prototypes and Production Rules: ,,1 Knowledge Representation for Computer Consultations, STAN-CS-80-814 (HPP-80-17), Stanford University, August 1980.
• 2: Kevin D. Ashley, Modelling legal argument: reasoning with cases and hypotheticals, University of Massachusetts, Amherst, MA, 1988
• 3: Kevin D. Ashley , Vincent Aleven, Toward an intelligent tutoring system for teaching law students to argue with cases, Proceedings of the 3rd international conference on Artificial intelligence and law, p.42-52, May 1991, Oxford, England [doi>10.1145/112646.112651]
• 4: L. Karl Branting, Reasoning with portions of precedents, Proceedings of the 3rd international conference on Artificial intelligence and law, p.145-154, May 1991, Oxford, England [doi>10.1145/112646.112664]
• 5: Clancey, W.J. (1983) The advantages of abstract control knowledge in expert system design, Proceedings A_AAI-83, pp. 74-78.
• 6: Empel, G. van (1992) Bescherming van de intellectuele eigendom, Kluwer, Deventer, NL.
• 7: Evans, J. ST B. T. (1988) The knowledge elicitation problem: a psychological perspective, Behaviour and information technology, 1988, vol. 7, no, 2, 111-130
• 8: Fernhout, F. (1989) Using a parallel distributed processing model as part of a legal expert system, In: A.A. Martino (ed) Pre-proc. of the IIi Int. Conf. on Logica, Informatica, Diritto, Florence 1989
• 9: P. Floréen , P. Myllymäki , P. Orponen , H. Tirri, Compiling object declarations into connectionist networks, AI Communications, v.3 n.4, p.172-183, Dec. 1990
• 10: Anne von der Lieth Gardner, An artificial intelligence approach to legal reasoning, MIT Press, Cambridge, MA, 1987
• 11: Groendijk, C (1992) Neural Schemata in Automated Judicial Problem Solving. In: Griitters, C.A.F.M., J.A.P.J. Breuker, H.J. van den Herik, A.H.J. Schmidt and C.N.J. de Vey Mestdagh (eds), Legal Knowledge Based Systems: Infromation Technology & Law, JURIX'92, Koninklijke Vermande, Lelystad, NL, 1992
• 12: Hopfield, J. J. (1982) Neural networks and physical ~ystems with emergent collective computational abih'ties. Proceedings of the National Academy of Science, USA, 79, 2554-2558
• 13: Miikkulainen, R. and M.G. Dyer (1989)A Modular Neural network Architecture for sequential paraphrasing ofscript-based stokes, Proceedings of the International Joint Conference on Neural Networks, Vol. II, iEE, USA
• 14: Minsky, M. (1975) A framework for representing knowledge. In P.H. Winston (Ed.), The psychology of computer vision (pp. 211-277). New York: McGraw- Hill
• 15: D. P. O'Neil, A process specification of expert lawyer reasoning, Proceedings of the 1st international conference on Artificial intelligence and law, p.52-59, May 27-29, 1997, Boston, Massachusetts, United States [doi>10.1145/41735.41742]
• 16: G. J. van Opdorp , R. F. Walker , J. A. Schrickx , C. Groendijk , P. H. van den Berg, Networks at work: a connectionist approach to non-deductive legal reasoning, Proceedings of the 3rd international conference on Artificial intelligence and law, p.278-287, May 1991, Oxford, England [doi>10.1145/112646.112682]
• 17: Prakken, H. (1993) Logical tools for modelling legal argument, Thesis, January 14, Vrije Universiteit, Amsterdam
• 18: E. L. Rissland , D. B. Skalak, Interpreting statutory predicates, Proceedings of the 2nd international conference on Artificial intelligence and law, p.46-53, May 1989, Vancouver, British Columbia, Canada [doi>10.1145/74014.74021]
• 19: Rumelhart, D.E. (1980) Schemata: The building blocks of cognition. In R. Spiro, B. Bruce, & W. Brewer (Eds), Theoretical issues in reading comprehension (pp. 33- 58). Hillsdale, NJ: Erlbaum
• 20: Rumelhart, D.E., McClelland, j.L. and the PDP Research Group (1988), Parallel Distributed Processing, Eighth printing, Cambridge, Massachusetts, MIT Press.
• 21: Kathryn E. Sanders, Representing and reasoning about open-textured predicates, Proceedings of the 3rd international conference on Artificial intelligence and law, p.137-144, May 1991, Oxford, England [doi>10.1145/112646.112663]
• 22: Schank, R.C. and R.P. Abelson (1977) Scripts, Plans, Goals, and Understanding, Erlbaum, Hillsdale, NJ
• 23: David B. Skalak , Edwin L. Rissland, Argument moves in a rule-guided domain, Proceedings of the 3rd international conference on Artificial intelligence and law, p.1-11, May 1991, Oxford, England [doi>10.1145/112646.112647]
• 24: Steels, L. (1988)Artificial intelligence and complex dynamics, AI-MEMO 88-2, Januari 9, 1988, Vrije Universiteit Brusse., AI Lab.
• 25: Verkade, D.W.F. & J.H. Spoor (1985)Auteursrecht, Kluwer, Deventer, NL.
• 26: George Vossos , John Zeleznikow , Tharam Dillon , Vivian Vossos, An example of integrating legal case based reasoning with object-oriented rule-based systems: IKBALS II, Proceedings of the 3rd international conference on Artificial intelligence and law, p.31-41, May 1991, Oxford, England [doi>10.1145/112646.112650]
• 27: Wildt, J.H. de, Quast J.A. (1989) Kenmerken van LEIDRAAD, een kennissysteem voor de werkloosheidswet, in: Proceedings AI toepassingen '89, SIC.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.1 MODELS AND PRINCIPLES
      H.1.2 User/Machine Systems
          Subjects: Human factors

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.0 General
          Subjects: Cognitive simulation
      I.2.1 Applications and Expert Systems
          Subjects: Law
      I.2.4 Knowledge Representation Formalisms and Methods
          Subjects: Frames and scripts; Predicate logic
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Graph and tree search strategies
  I.5 PATTERN RECOGNITION
      I.5.1 Models
          Subjects: Neural nets
      I.5.2 Design Methodology
          Subjects: Classifier design and evaluation; Feature evaluation and selection

General Terms:
Human Factors, Legal Aspects