Towards annotating and extracting textual legal case factors

Case based reasoning is a crucial aspect of common law practice, where lawyers select precedent cases which they use to argue for or against a decision in a current case. To select the precedents, the relevant facts (the case factors) of precedent cases must be identified; the factors predispose the case decision for one side or the other. As the factors of cases are linguistically expressed, it is useful to provide a means to automate the identification of candidate passages. We outline and report the results of our approach to the identification of legal case factors which follows a bottom-up knowledge heavy strategy and uses the General Architecture for Text Engineering system. Salient lexical items are selected, concept classes of related terms are created, and annotation rules for simple and compound concepts are provided. The annotated concepts can be extracted from the cases, and cases can be classified with respect to the concepts. In addition to supporting extraction of relevant information, the approach has a didactic use in helping to train lawyers to perform close textual analysis. Finally, we carry out an initial collaborative, online annotation exercise using GATE TeamWare in order to develop a gold standard. 1