A10aw

The LLT Lab works with its collaborators to develop software applications that will assist clients, lawyers and legal decision makers in making legal arguments. Such applications range from automatically annotating legal texts for argument-related elements, to document assembly applications that use extracted information to generate legal documents (programs that go well beyond the template-and-variable-value designs of today’s state-of-the-art). For example, as reported in our 2015 article reporting on a proof-of-feasibility experiment for our project on automating argument mining, the conceptual markup of documents was done automatically using LUIMA, a law-specific semantic extraction toolbox based on the UIMA framework. The system consisted at that time of modules for automatic sub-sentence level annotation, machine-learning-based sentence annotation, basic retrieval using Apache Lucene, and a machine-learning-based re-ranking of retrieved documents. New software analytics are being developed, at the same time as we improve the performance of existing analytics.