Precedent-based legal reasoning and knowledge acquisition in contract law: A process model
ICAIL '87 Proceedings of the 1st international conference on Artificial intelligence and law
Reasoning about 'hard' cases in Talmudic law
ICAIL '87 Proceedings of the 1st international conference on Artificial intelligence and law
Legal data modeling: The prohibited transaction exemption analyst
ICAIL '87 Proceedings of the 1st international conference on Artificial intelligence and law
Learning and reasoning by analogy
Communications of the ACM
Simulation modeling of the criminal justice system and process
WSC '77 Proceedings of the 9th conference on Winter simulation - Volume 1
The applications of artificial intelligence to law: a survey of six current projects
AFIPS '81 Proceedings of the May 4-7, 1981, national computer conference
Learning to understand contractual situations
IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 1
Hi-index | 0.02 |
This paper describes the prototype for a computer system that can perform a simple kind of legal analysis. The system user, who is presumed to be a lawyer, describes to the system a hypothetical set of facts. The system determines the extent to which these facts fall within certain legal doctrines (by syllogism), or near to these doctrines (by analogy). During this process, the system may ask the user for additional facts. The system then tells the user of its determinations and of the logic behind its conclusions with reference to judicial decisions and other legal authority. The prototype system communicates with the user in a computer language (called Preliminary Study Language) designed to be translatable into and out of English but natural-language processing techniques, based on case grammar, that are currently being developed in other research. As the basis for this analysis, structural machine models are built to represent legally-relevant human activity and doctrines of law. The primitive components in these structures represent simple things and relations (like persons, firearms, hitting, near, etc.) in the everyday world of human affairs. These things and relations are classified hierarchically into categories. They are assembled into facts comprising two things and the relation between them. Facts, in turn, are assembled into more complicated structures called situations, which are represented in terms of component elements, or in terms of alternative types, or both. These situational structures are used to represent the hypothetical facts being analyzed as well as the factual content of legal doctrines. The factual situations of specific cases provide examples and counter-examples that behave as alternative types of the situational components of more general legal doctrine. The prototype system contains representations for doctrine involving battery and assault. Analysis is performed by decomposing the situations that represent legal doctrines according to their elements and their types. When this decomposition reaches the level of things and relations, these things and relations, together with their situational structure, are matched against the things and relations contained in the hypothetical facts. The matching of individual things and relations is accomplished by reference to their hierarchical categorization.