Extracting meaningful entities from regulatory text: Towards automating regulatory compliance

Abstract

Extracting essential meaning from the regulatory text helps in the automation of the Compliance Management (CM) process. CM is a process where organizations assure that the processes are run according to requirements and expectations. However, extraction of meaningful text from regulatory guidelines comes with many research challenges such as dealing with different document-format, implicit document-structure, textual ambiguity and complexity. In this paper, the extended version of the Semantic-ART framework is described, which focuses on tackling the challenges of document-structure identification and regulatory-entity extraction. An initial result has shown an inspirational result as compared to the previous version of the framework.