A natural language based legal expert system for consultation and tutoring—the LEX project

ABSTRACT

The LEX (Legal Expert System) project is one of the European based projects investigating legal expert systems from both a professional and a teaching perspective. The project is a cooperative project between the University of Tübingen and IBM Germany and developed out of research into a User Specialty Language system (USL) for natural language queries to a relational data base. The LEX system has as its main components a Natural Language Analyzer for analysis and logic representation of written texts. A Knowledge Base holding; sources from the legal codes, explanations from legal commentaries, some common sense knowledge, and a lexicon of approximately 20000 words. Finally a Deductive Component based upon tableau calculus, conducts inference within the system. The system has as its primary aim to enable lawyers to input in natural language a set of case facts and to ask questions on the juridical issues connected to those facts. Dialogue is controlled enabling intelligent explanation to the user when required. A secondary aim is to provide additional components so as to enable the system to tutor on the legal domain held within the system. The development of the system has enabled the project team to gain insights into the problem of formalization of legal rules within the German legal system.

REFERENCES

• 1: Alschwee, B. and Grundmann, S., "Systemdesign f/fir ein computergest/itztes juristisches Expertensystem", D. Fiedler, B. Traunmfiller (Eds.), Proceedings GI Workshop Formalisierung des Rechts, Schweitzer, Bonn u. M/inchen (1985)
• 2: Anderson, J.R., Boyle, C.F., Yost, G., ~lntelligent Tutoring Systems," Science, 228, 1985, pp. 456-462.
• 3: Ashley, K. and E. Rissland, "Towards Modelling Legal Argument." in Martino, A. (cd). Logica, Informatica, Diritto, Proceedings of the Second Conference on Legal !nformatics, Florence, Italy (September 1985), pp. 381-397.
• 4: Brigitte Barnett , Hubert Lehmann , Magdalena Zoeppritz, A word database for natural language processing, Proceedings of the 11th coference on Computational linguistics, August 25-29, 1986, Bonn, Germany [doi>10.3115/991365.991493]
• 5: Burris, R. "Critical Features of Microcomputer-Based Exercises for Effective Teaching and Learning of Law.~ (1985) IBM ACi5 Proceedings.
• 6: Clancey, W., "The Epistemology of a Rule-Bases Expert System - A Framework for Explanation", (1983) Artificial intelligence 18 p 215.
• 7: Clark, H.H., and Marshall, L., "Definite References and Mutual Knowledge~, in A.K.Joshi, B.L.Webber, 1.A. Sags (eds)' Elements of Discourse Understanding. Cambridge University Press, (1981), pp 10-64.
• 8: F Di Primio , G Brewka, BABYLON—kernel system of an integrated environment for expert system development and operation, 5th international workshop, Vol. 1 on Expert systems & their applications, p.573-583, December 1986, Avignon, France
• 9: Franz Guenthner , Hubert Lehmann, Automatic construction of discourse representation structures, Proceedings of the 22nd annual meeting on Association for Computational Linguistics, p.398-401, July 02-06, 1984, Stanford, California
• 10: Franz Guenthner , Hubert Lehmann , Wolfgang Schönfeld, A theory for the representation of knowledge, IBM Journal of Research and Development, v.30 n.1, p.39-56, Jan. 1986
• 11: Haft, F. "The Joint Project of IBM Germany and the University of T/ibingen LEX (Linguistic and Logic Based Expert System in Law)r, The Law and Computers Association of Japan - Journal of the Law and Computers Vol. 5 (1987) (in press)
• 12: Hartley, J.R. and Sleeman, D.H., '~T'owards Intelligent Teaching Systems~, Int. J. of Man*Machinc Stu(lics. 1973.
• 13: Jesse M. Heines , Tim O'Shea, The design of a rule-based CAI tutorial, International Journal of Man-Machine Studies, v.23 n.1, p.1-25, July 1985 [doi>10.1016/S0020-7373(85)80021-3]
• 14: Holmes, O.W., "The Common Law", (l g8 I), p 1.
• 15: iBM (1993): SQL Data System, General Information, GJ-124-5013, International Business Machines Corporation, Endicott, New York.
• 16: Kamp, H.f A Theory of Truth and Semantic Representation~, Grocncndijk ct al. (eds.), Formal Methods in the Study of Language. Mathematical Centre Tract, Amsterdam (1981). Reprint in' Groencndijk ct al. (eds.), Truth, Representation and Information. GRASS 2, Dordrccht: Foris.
• 17: Lehmann, Hu., Ott, N. and Zoeppritz, M., "A Multilingual Interface to Databases", i EEE Database Enginccring Bulletin, Vol. 8, No. 3, New York (1985).
• 18: SchSnfeld, W., 'Prolog Extensions Based on Tableau Calculus', Proceedings of the 9th International Joint Conference on Artificial Intelligence, Voi. 2, Los Altos, USA (1985), pp. 730-732.
• 19: Wetter, Th., 'Common Sense Knowledge in Expert Systerns~, Proceedings NATO Advanced Study Institute, Porto, August 1986, Springer, Berlin (1987) (in press)
• 20: Wirth, R., "Halbautomatische Erweiterung eines bestchcnden Thesaurus", diploma thesis, Heidelberg University and Fachhochschule Heilbronn (1984).
• 21: Zoeppritz, M., "Syntax for German in the User Specialty Languages System", Niemeyer, T/ibingen (1984).

INDEX TERMS

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

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.1 Logical Design
          Subjects: Data models
      H.2.4 Systems
          Subjects: Query processing

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

General Terms:
Design, Human Factors