Knowledge discovery in the legal domain

Whilst cases have been regularly used in building legal case based reasoners, they have rarely been used as a means of automated discovery of legal knowledge. Significant obstacles must be overcome if knowledge discovery techniques are to be applied in the legal domain. We argue that the use of domain expertise is vital and that an abundance of commonplace cases is necessary. Even with appropriate data, knowledge discovery techniques in law must deal with contradictory cases and use statistical techniques in order to define error and estimate performance. We illustrate these points by describing the use of the cross validation resampling technique, our own error heuristic and the method we use for dealing with contradictions for the training of neural networks in the domain of property proceedings in Australian Family Law