Knowledge discovery in the Split Up project
John Zeleznikow, Andrew M. Stranieri · 1997
Knowledge discovery techniques have not been applied extensively in legal domains despite potential benefits in the automated generation of legal knowledge from data.We suggest that more attention must be placed on the collection of data from cases that are ordinary and which are currently considered to be uninteresting for the full benefits of knowledge discovery to be realised.However, even with appropriate data, knowledge discovery techniques in law must deal with contradictory cases and must 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.