An Information Infrastructure for Government Regulation Analysis and Compliance Assistance

1 Project Overview The complexity and diversity of government regulations make understanding the regulations a non-trivial task. One of the issues is the existence of multiple sources of regulations and interpretive guides; the latter are often independent of governing bodies. In this work, we describe a research prototype system that combines text mining and knowledge management techniques to help better manage, understand and analyze regulatory documents. This regulatory information infrastructure includes three integral parts: a document repository, a tool for similarity analysis and a compliance assistance system. This paper first presents the development of a legal corpus with multiple sources of regulatory documents consolidated into a unified format. A shallow parser is developed to consolidate different regulations into a unified XML format, which is well suited for handling semi-structured data such as legal documents. Important features, such as concepts, measurements, definitions and so on, are extracted and incorporated into the corpus by using handcrafted rules and text mining tools. A regulation compliance assistance system is introduced next, where First Order Predicate Calculus (FOPC) logic sentences are implemented to help users to perform compliance check in a question and answer session. Finally, a similarity analysis for regulations is developed, where Information Retrieval (IR) and structural matching techniques are used to identify related provisions among regulations.