Neural networks and open texture

ABSTRACT

In this paper some experiments designed to explore the suitability of using neural nets to tackle problems of open texture in law are described. Three key questions are investigated: can a net classify cases successfully; can an acceptable rationale be uncovered by an examination of the net; and can we derive rules describing the problem from an examination of the net?

REFERENCES

• 1: Kevin D. Ashley, Modeling Legal Arguments: Reasoning with Cases and Hypotheticals, MIT Press, Cambridge, MA, 1991
• 2: Bench-Capon, T.J.M., Sergot, M.J. {1985} Towards a ntle-based representation of open texture in law. in Computing Power and Legal Language (Walter, C., Ed). Greenwood/Quorum Press, New York, 1988, pp 39-60.
• 3: Laurent Bochereau , Danièle Bourcier , Paul Bourgine, Extracting legal knowledge by means of a multilayer neural network application to municipal jurisprudence, Proceedings of the 3rd international conference on Artificial intelligence and law, p.288-296, May 1991, Oxford, England [doi>10.1145/112646.112683]
• 4: Capper, P.N., Susskind, R.E. {1988} Latent Damage Law - Tl, e Expert System. Butterworths, London, 1988.
• 5: G. Greenleaf , A. Mowbray , A. L. Tyree, Expert systems in law: The datalex project, Proceedings of the 1st international conference on Artificial intelligence and law, p.9-17, May 27-29, 1997, Boston, Massachusetts, United States [doi>10.1145/41735.41737]
• 6: Gorman, R.P., and Sejnowski, T.J., {1988}, Analysis of Hidden Units in a Layered Network Trabied to Classify Sonar Targets Neural Networks 1 pp75-89.
• 7: Leighton, R.L., {1991}, T12e Aspirin/MIGRAINES Software Tools User Manual, Release V5. The Mitre Corporation.
• 8: L. T. McCarty, A language for legal Discourse I. basic features, Proceedings of the 2nd international conference on Artificial intelligence and law, p.180-189, May 1989, Vancouver, British Columbia, Canada [doi>10.1145/74014.74037]
• 9: M. J. Sergot , F. Sadri , R. A. Kowalski , F. Kriwaczek , P. Hammond , H. T. Cory, The British Nationality Act as a logic program, Communications of the ACM, v.29 n.5, p.370-386, May 1986 [doi>10.1145/5689.5920]
• 10: Sestito, S., and Dillon, T., {1992} Automated IO, owledge Acquisition of Rules with Continuously Valued Attribtttes, Proceedings of the 12th International Conference on Expert Systems, Avignon, 1992. EC2, pp645- 56.
• 11: Walker, R., {1992} An Expert Systems Architecture for Heterogeneous Do,2ains, Doctoral thesis, Vrige Univeriteit of Amsterdam.
• 12: J. Zurada, Introduction to artificial neural systems, West Publishing Co., St. Paul, MN, 1992

INDEX TERMS

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

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Connectionism and neural nets

General Terms:
Experimentation, Legal Aspects, Performance