Expert Systems in Law: The DataLex Project
Proceedings of the 1st International Conference on Artificial Intelligence and Law, ACM Press, 1987, 9-17
13 Pages Posted: 12 May 2013
Date Written: December 1, 1987
This paper presents the development by the DataLex Project, a joint research project by the authors, of a software ‘shell’ specifically suited to the development of legal expert systems, and its use to develop a number of experimental applications programs used for teaching and demonstrations in several Australian universities. The paper considers a number of characteristics which make the development of legal expert systems different in character from the development of similar systems in engineering, medicine and the natural sciences. These differences, together with some practical constraints, has been responsible for the particular form which the software tools have taken.
We argue there are a number of systems which have been built or are being built by people whose primary interest and training is in computer science and who fundamentally misunderstand the nature of law and legal reasoning, primarily widespread misconception that law is a simple system of rules and that legal inference consists of a simple deductive application of these rules. We challenge the view that there is need to construct "deep conceptual" models before effective legal expert systems may be built, concluding that it is an empirical problem which may only be resolved by building systems and evaluating their performance. The design criteria for the software and applications developed by the DataLex Project are then set out, and the shell and a number of resulting applications described. The shell includes both a decision network module (LES:DN) and a module for precedent analysis by nearest neighbour discriminant analysis (PAANDA). A full text retrieval system (AIRS) is intended to be integrated into the shell, and the reasons why this is necessary are explained.
Note: This was the first published paper concerning the DataLex project, and the first paper presented at the 1st ICAIL Conference.
Keywords: legal information systems, expert systems, artificial intelligence, legal reasoning, Australia
Suggested Citation: Suggested Citation