Dr. Adam Wyner of the University of Leeds Centre for Digital Citizenship has posted Weaving the Legal Semantic Web with Natural Language Processing, on the VoxPopuLII Blog, published by the Legal Information Institute at Cornell University Law School.
Dr. Wyner’s post provides an introduction to the use of Natural Language Processing (NLP) for adding structure to digital legal texts, representing the meaning of those texts, and making those texts and their meaning processable by machines. Legal texts whose meaning can be recognized and processed by machines are key components of the legal Semantic Web. Dr. Wyner explains how XML can be used to represent individuals, organizations, and ideas — and the relationships between them — in legal texts, in a manner that computers can recognize and process. Dr. Wyner then discusses how NLP tools — such as the General Architecture for Text Engineering (GATE) — can be used to automate the process of marking up legal texts in XML and representing the key entities and relationships in those texts.
Dr. Wyner’s post will be of interest to all those who publish law in digital formats, those seeking an introduction to the legal Semantic Web, and to researchers studying the legal Semantic Web, other aspects of legal knowledge representation, the use of Natural Language Processing for legal text processing, and legal information retrieval.