Internationalisation and the expansion of the European Union have created a situation where the need for legal information from foreign countries and from different legislative levels is greater than ever before. This information is increasingly becoming available in digital form due to the increase in legal information repositories on the Internet. In spite of this, users of European legal inf...

We can observe and measure how legal decision makers use formal legal authorities, but there is no way to empirically test the determinative capacity of legal doctrine itself. Yet discussions of empirical studies of judicial behavior sometimes conflate judges’ attention to legal rules with legal rules determining outcomes. Doctrinal determinacy is not the same thing as legal predictability. The...

A test input for an object-oriented program typically consists of a sequence of method calls that use the API defined by the program under test. Generating legal test inputs can be challenging because, for some programs, the set of legal method sequences is much smaller than the set of all possible sequences; without a formal specification of legal sequences, an input generator is bound to prod...

Applying Bayesian data analysis to model a computer-supported peerreview process in a legal class writing exercise yielded pedagogically useful information about student-understanding of problem-specific legal concepts and of more general domain-related legal writing criteria and about the criteria’s effectiveness. The approach suggests how AI and Law can impact legal education.

York University participated in the legal track this year. For this track, we developed an Okapi-based Legal Search Engine (LSE) v1.0. Our experiments mainly focused on evaluating the effect of a probabilistic text retrieval model on the legal domain. In order to address the special problems in legal text retrieval, new automatic feedback methods and term weighting methods are proposed and tested.

Most legal expert systems attempt to implement complex models of legal reasoning. But the utility of a legal expert system lies not in the extent to which it simulates a lawyer’s approach to a legal problem, but in the quality of its predictions and of its arguments. A useful legal expert system should be capable of producing advice similar to that which one might get from a lawyer, so it shoul...

Most legal decision support systems have generally operated in domains with well-understood norms. Hence reasoning has been represented by a combination of rule-based and case-based reasoning. However, we analyse legal domains in which decision makers are allowed a significant amount of discretion. We argue that if the domain is bounded, and a sufficient number of commonplace cases exist, then ...

This Article proposes a novel technique for characterizing the relative determinacy of legal decision-making. I begin with the observation that the determinacy of legal outcomes varies from context to context within the law. To augment this intuition, I develop a theoretical model of determinate legal decision-making. This model aims to capture the essential features that are typically associat...

Jurimetrics, the empirical study of legal phenomena, is generally associated with the quantitative analysis of legal cases. However, an interesting field, which can also be seen as a part of jurimetrics, is the analysis of legal word use. The subject matter of this examination was a broad selection of British legal documents, both case reports and legislation. Using quantitative methods develop...