En route to data mining in legal text corpora: clustering, neural computation, and international treaties

The huge amount of data in legal information systems requires a new generation of techniques and tools to assist lawyers in analyzing data and finding critical nuggets of useful knowledge. A promising approach for data mining in legal text corpora is classification. What we are looking for are powerful methods for the exploration of such libraries whereby the detection of similarities between documents is the overall goal. These methods may be used to gain insight in the inherent structure of the various items contained in a text archive. In this paper, we present the results from a case study in legal document classification based on an experimental document archive comprising important treaties in public international law. The essentials of our approach are the usage of a vector space document representation and the utilization of an unsupervised artificial neural network for document classification.