Exploiting the Rich Document Structures and Network Topology of Legal Information Systems

The move toward on-line publishing of legal documents in the public domain has made extra information available by way of mark-up for electronic publishing. Legal Concepts that were once implicit in documents are now explicit and further inferences can now be drawn through computation however the quality and extent of this information varies. This paper discusses the application of web techniques to the legal system for the ranking of related legal concepts. We demonstrate how these techniques can be adapted and applied to the legal system and how strategies can be used to optimize the best combination of techniques depending on the quality of the source information. Courts and legislatures create and distribute laws through documents that serve as the primary sources of law within legal systems. With the increase in on-line publishing, these documents are being marked-up with greater quantities of information particularly with links to other related sources within the legal system.