Can legal knowledge be derived from legal texts?

ABSTRACT

Knowledge acquisition is undoubtedly one of the major bottle-necks in the development of legal expert systems. Usually the knowledge is collected by knowledge engineers who are forced to make their own interpretations of the knowledge in order to map it on a knowledge representation technique, thus resulting into erroneous and legally unacceptable interpretations of the law. The aim of NOMOS (an EC supported project under the ESPRIT II initiative) was to assist the knowledge engineer by providng tools that perform semi-automatic knowledge acquisition from legal texts in Italian and French. This paper reports on the results of the first evaluation of the knowledge collected by these tools. The evaluation was performed by complementing the tools with a fully functional expert system that accepted the generated knowledge bases and allowed experts to test the completeness of the knowledge through a series of interactive consultations. The knowledge base used for this evaluation was derived from the text for the Italian Value Added Tax Law. The text was pre-processed in its ASCII form by the Nomos tools and the generated knowledge base was filtered through to a conventional expert system shell to generate the evaluation expert system. Knowledge extracted directly from text was converted into a hybrid of production rules and Conceptual Graphs. [see SOWA 1984] Knowledge collected from other sources, such as previously resolved cases, explanations of terms and examples, were linked to the knowledge base using an automated hypertext technique. [see KONSTANTINOU & MORSE 1992] Finally, the expert system was tested using real-life cases supplied by the Italian ministry of finance.

REFERENCES

• 1: T. J. M. Bench-Capon, Knowledge-based systems and legal applications, Academic Press Professional, Inc., San Diego, CA, 1991
• 2: Bn~o J. & HARVOLD T, Legal Decisions and Information Systems, Universittsforlaget, Oslo 1977
• 3: CIAMPI C. (Ed.), Artificial Intelligence and Legal Information Systems, Volume 1, edited versions of selected papers from the international conference on ~Logic, Informatics, Law", Florence April 1981, North Holland 1982
• 4: CODICE LMPOSTA VALORE AGGiUNTO, Selected papers from the periodical on the interpretation of article 7 of the Italian VAT Law, including case-law and bibliography.
• 5: DECRETO DEL PRESIDENTS DELLA REPUBLICA, (DPR) N.633, 26/10/72 = The Official Text of the Italian VAT Law.
• 6: Dmscrrvs (6TX OF 17 MAY 1977), on the harmonisation of VAT Law, OJ L 145, 13/06/77
• 7: ESPRIT-Dec IL-31-50-01, Annex N, Representational Issues Concerning Art.7 (Final Results of Annex I), 20-Mar=92
• 8: EsPRIT-Dec SG-11-40-06, Type Hierarchy for the Italian Domain, 20-Mar-92
• 9: EsPRIT-Dec SG-31-50-01, Legal Knowledge Engineering; A Case Study (A~rNA GIA~E~n) - First Results, 15-Se1~91
• 10: EsPs~r-Doc TE-10-40-01, Normative Field Selection & Domain Analysis (WP1- IRETN), 16-Jul-91
• 11: EsPVdT-Doc TE-31-40-01, Design of ILAM module for NOMOS, 16-Sep-91
• 12: ESPRiT-Dec TE-33-40-03, by BASmZ R., ILAM, Taxonomic Relation Acquisition within the SLAT subsystem.
• 13: FA~OUSS Jr Conceptual Graphs for Natural Language Semantics and Deduction, a Text Analysis and Query/Answer SysCem Based on Conceptual Graphs in ACAI'89 Neuchatel
• 14: Jean Fargues , Marie-Claude Landau , Anne Dugourd , Laurent Catach, Conceptual graphs for semantics and knowledge processing, IBM Journal of Research and Development, v.30 n.1, p.70-79, Jan. 1986
• 15: Anne von der Lieth Gardner, An artificial intelligence approach to legal reasoning, MIT Press, Cambridge, MA, 1987
• 16: 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
• 17: HARTLEY & COOMBS, Reasoning with Graph Operations in Sowa(Ed.) Principles of Semantic Networks, Morgan Kaufmann, California, 1991
• 18: ICAIL PROCEEDn~Os, The Third International Conference on Artificial Intelligence and Law Proceedings, Oxford 1991
• 19: ILAM OUTPUT, The ILAM output in ASCII format
• 20: KAMEL M. & Qun~?ANA Y., A Graph Based Knowledge Retrieval System, IEEE Conference on Systems, Man and Cybernetics, Nov. 4-7th 1990, Los Angeles, California.
• 21: Albert W. Koers , M. Smith , D. Kracht , J.M. Smits , M.C.M. Weusten, Knowledge Based Systems in Law: In Search of Methodologies and Tools, Kluwer Law Intl, 1989
• 22: V. Konstantinou , P. Morse, Electronic documentation system: using automated hypertext techniques for technical support services, Proceedings of the 10th annual international conference on Systems documentation, p.1-6, October 13-16, 1992, Ottawa, Ontario, Canada [doi>10.1145/147001.147002]
• 23: LANDAU M.=C., Solving Ambiguities in the Semantic Representation of Texts IBM France Scientific Center, 1991
• 24: LANZARONB ET AL, Programmazione in Logica della Legge sull' IVA, Dipartimento di Scienze dell' Informazione, Universita degli Studi di Milano, 1991
• 25: LEHMAN H, Legal Concepts in a Natural Language Based Expert System in Ratio Juris V.3, No.2, July 1990
• 26: LEITH P., Legal Expert Systems: Misunderstanding the Legal Process in Computers and Law, 49, September 1986
• 27: LE~Trt P., Legal Expertise and Legal Expert Systems, in Yearbook of Law Computers and Technology V.2 1986
• 28: MARZANI P. & TISCORN~ D. (Eds.), Sistemi Esperti Giuridici, L' Intelligenza Artificiale applicata al Diritto, Milano 1989
• 29: Antonio A. Martino, Deontic Logic, Computational Linguistics and Legal Information Systems, Elsevier Science Inc., New York, NY, 1982
• 30: MARTiNO A. & SOCCI-NATAL! F. (Eds.), Automated Analysis of Legal Texts, 2nd international Congress Logica, Informatica, Diritto Florence, Palazzo dei Congressi, 3-6 September 1985, North Holland 1986
• 31: MouLn~ B. & ROUSSEAU D, A Knowledge Acquisition System for Analysing Prescriptive Texts, in the 5th AAAI-Sponsored Knowledge Acqusition for Knowledge Based Systems Worksshop, Banff, Canada, November 1989
• 32: MouLn~ B. & ROUSSEAU D., Designing deontic knowledge bases from regulation texts, in Knowledge Based Systems ~oL3 No.2 June 1990
• 33: MouL~ B. & RoussEAu D., Extracting Logical Knowledge from Prescriptive Texts in order to build Deontie Knowledge Base, in Proceedings of the 6th Banff Knowledge Acquisition for Knowledge-Based Systems Workshop, Banff, Canada 6-11 October 1991
• 34: MussETro ET AL, A Multi Layered Architecture for Automatic Knowledge Acquisition from Legal Texts, Tesciel & Sogei Group for Nomos, 1991
• 35: Yuri Quintana , Mohamed Kamel , Andrew Lo, Graph-based retrieval of information in hypertext systems, Proceedings of the 10th annual international conference on Systems documentation, p.157-168, October 13-16, 1992, Ottawa, Ontario, Canada [doi>10.1145/147001.147022]
• 36: SEMANTIC L~XICON, The Nomos Sematic Lexicon Version 15-Jun- 92
• 37: SMiTh J.C., GELBART D., & G~M D., A Procedure for Creating Expert Systems in Law, in Computers and Law Vol.3, Issue 3, July 1992, page 23
• 38: SOGEI GROUP, A Qualification Assistant for the VAT Law, A Proposal for Nomos Application, Rome 18-Jun-92
• 39: John F. Sowa, Definitional mechanisms for restructuring knowledge bases, Methodologies for intelligent systems, 5, Elsevier North-Holland, Inc., New York, NY, 1991
• 40: SOWA J. F., Toward the Expressive Power of Natural Language in Sowa(Ed.) Principles of Semantic Networks, Morgan Kaufmann, California, 1991
• 41: J. F. Sowa, Conceptual structures: information processing in mind and machine, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1984
• 42: John F Sowa , Eileen C Way, Implementing a semantic interpreter using conceptual graphs, IBM Journal of Research and Development, v.30 n.1, p.57-69, Jan. 1986
• 43: R. Susskind, Expert systems in law, Oxford University Press, Inc., New York, NY, 1987
• 44: TYREE A., The Logic Programming Debate, in Journal of Law and Information Science, Vol.3 (1992), N.1 p.lll
• 45: UW-AIRG*, KNOWLEDCE BASE (in English and italian) for article 7 of the Nomos project, Version 26-Oct-92
• 46: Paola Velardi , Maria Teresa Pazienza , Mario De' Giovanetti, Conceptual graphs for the analysis and generation of sentences, IBM Journal of Research and Development, v.32 n.2, p.251-267, March 1988
• 47: WIDDISON 1~, PgITCHARD F. &, ROBINSON W., Expert Systems Meets Hypertext: The European Conflicts Guide, in Journal of Law and Information Seienee, VoL3 (1992), N.1 p.82
• 48: ZELEZNIKOW J. & HUNTER D., Rationales for the Continued Development of Legal Expert Systems in Journal of Law and Information Science, Vol.3 (1992), N.I p.96

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

General Terms:
Languages, Legal Aspects